I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l
E
ng
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
,
p
p
.
2
1
4
~
2
2
2
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
7
.
i
1
.
pp
2
1
4
-
2
2
2
214
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
An
enha
nce
d pr
e
dictive mo
delling
framewo
rk
for hi
g
hly
a
ccurate non
-
a
lco
ho
lic f
a
tt
y
liver
di
sea
se foreca
sting
Nidh
i A
ro
ra
1
,
Sh
il
pa
Sriv
a
s
t
a
v
a
2
,
Aprna
T
ripa
t
hi
3
,
Va
runa
G
up
t
a
2
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
K
a
l
i
n
d
i
C
o
l
l
e
g
e
,
U
n
i
v
e
r
si
t
y
o
f
D
e
l
h
i
,
D
e
l
h
i
,
I
n
d
i
a
2
S
c
h
o
o
l
o
f
S
c
i
e
n
c
e
s
,
C
h
r
i
st
U
n
i
v
e
r
si
t
y
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
D
a
t
a
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
M
a
n
i
p
a
l
U
n
i
v
e
r
s
i
t
y
J
a
i
p
u
r
,
J
a
i
p
u
r
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
14
,
2
0
2
4
R
ev
is
ed
Au
g
26
,
202
4
Acc
ep
ted
A
ug
31
,
2
0
2
4
No
n
-
a
lco
h
o
li
c
fa
tt
y
l
iv
e
r
d
ise
a
se
(NA
F
LD)
is
a
c
h
ro
n
ic
m
e
d
ic
a
l
a
il
m
e
n
t
c
h
a
ra
c
teriz
e
d
b
y
a
c
c
u
m
u
latio
n
o
f
e
x
c
e
ss
iv
e
fa
t
in
th
e
l
iv
e
r
o
f
n
o
n
-
a
lco
h
o
li
c
p
a
ti
e
n
ts.
I
n
a
b
se
n
c
e
o
f
a
n
y
e
a
rly
v
isib
le
in
d
ica
ti
o
n
s,
a
p
p
li
c
a
ti
o
n
o
f
m
a
c
h
in
e
lea
rn
in
g
b
a
se
d
p
re
d
icti
v
e
tec
h
n
i
q
u
e
s
fo
r
e
a
rly
p
re
d
ictio
n
o
f
N
AF
LD
a
re
q
u
it
e
b
e
n
e
ficia
l.
Th
e
o
b
jec
ti
v
e
o
f
th
is
p
a
p
e
r
is
t
o
p
re
se
n
t
a
c
o
m
p
lete
fra
m
e
wo
rk
fo
r
g
u
id
e
d
d
e
v
e
lo
p
m
e
n
t
o
f
v
a
ried
p
re
d
icti
v
e
m
a
c
h
in
e
lea
rn
in
g
m
o
d
e
ls
a
n
d
p
re
d
ict
NA
F
LD
d
ise
a
se
with
h
i
g
h
a
c
c
u
ra
c
y
.
T
h
e
f
ra
m
e
wo
rk
e
m
p
lo
y
s
ste
p
–
by
-
ste
p
d
a
ta
q
u
a
li
ty
e
n
h
a
n
c
e
m
e
n
t
t
o
m
e
d
ica
l
d
a
ta
su
c
h
a
s
c
lea
n
in
g
,
n
o
rm
a
li
z
a
ti
o
n
,
d
a
ta
u
p
sc
a
li
n
g
u
sin
g
S
M
OTE
(fo
r
h
a
n
d
li
n
g
c
las
s
imb
a
lan
c
e
s)
a
n
d
c
o
rre
latio
n
a
n
a
ly
sis
-
b
a
se
d
fe
a
tu
re
se
lec
ti
o
n
t
o
p
re
d
ict
NA
F
LD
with
h
ig
h
a
c
c
u
ra
c
y
u
sin
g
o
n
l
y
c
li
n
ica
ll
y
re
c
o
rd
e
d
i
d
e
n
ti
fiers
.
Co
m
p
re
h
e
n
si
v
e
c
o
m
p
a
ra
ti
v
e
a
n
a
l
y
sis
o
f
p
re
d
ictio
n
re
su
lt
s
o
f
se
v
e
n
m
a
c
h
in
e
lea
rn
in
g
p
re
d
ictiv
e
m
o
d
e
ls
is
d
o
n
e
u
sin
g
u
n
p
r
o
c
e
ss
e
d
a
s
we
ll
a
s
q
u
a
li
t
y
e
n
h
a
n
c
e
d
d
a
ta.
As
p
e
r
th
e
o
b
se
rv
e
d
re
su
lt
s,
XG
Bo
o
st,
ra
n
d
o
m
f
o
re
st
a
n
d
n
e
u
ra
l
n
e
two
r
k
m
a
c
h
in
e
lea
rn
i
n
g
m
o
d
e
ls
re
p
o
rted
si
g
n
if
ica
n
t
ly
h
i
g
h
e
r
a
c
c
u
ra
c
ies
with
imp
r
o
v
e
d
‘
AUC
’
a
n
d
‘
ROC
’
v
a
lu
e
s
u
si
n
g
p
re
p
r
o
c
e
ss
e
d
d
a
ta
in
c
o
n
tras
t
to
u
n
p
r
o
c
e
ss
e
d
d
a
ta.
Th
e
p
re
d
ictio
n
re
su
lt
s
a
re
a
lso
a
s
se
ss
e
d
o
n
v
a
rio
u
s
q
u
a
li
ty
m
e
tri
c
s
su
c
h
a
s
‘
a
c
c
u
ra
c
y
’
,
‘
f1
-
sc
o
re
’
,
‘
p
re
c
isio
n
’
,
a
n
d
‘
re
c
a
ll
’
sig
n
ifi
c
a
n
tl
y
su
p
p
o
rt
th
e
n
e
e
d
f
o
r
p
re
se
n
ted
m
e
th
o
d
o
l
o
g
ies
f
o
r
q
u
a
li
tati
v
e
NA
F
LD
p
re
d
ictio
n
m
o
d
e
ll
in
g
.
K
ey
w
o
r
d
s
:
C
h
r
o
n
ic
d
is
ea
s
es
C
las
s
i
m
b
alan
ce
C
las
s
if
icatio
n
NAFL
D
Pre
d
ictiv
e
m
o
d
ellin
g
SMOT
E
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Nid
h
i A
r
o
r
a
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
Kalin
d
i Co
lleg
e
,
Un
iv
e
r
s
ity
o
f
Delh
i
Delh
i
1
1
0
0
0
8
,
I
n
d
ia
E
m
ail: n
id
h
iar
o
r
a@
k
alin
d
i.d
u
.
ac
.
in
1.
I
NT
RO
D
UCT
I
O
N
C
h
r
o
n
ic
m
etab
o
lic
d
is
o
r
d
er
s
a
r
e
d
is
o
r
d
er
s
th
at
ar
e
lo
n
g
last
in
g
an
d
ar
e
ca
u
s
ed
d
u
e
to
d
is
r
u
p
tio
n
s
i
n
th
e
m
etab
o
lis
m
o
f
h
u
m
an
b
o
d
y
[
1
]
.
T
h
ese
ca
teg
o
r
ies
o
f
d
i
s
ea
s
es
ar
e
p
r
im
ar
ily
n
o
t
in
d
icativ
e
u
s
in
g
g
en
er
al
p
h
y
s
ical
an
d
clin
ical
ass
ess
m
en
ts
,
b
u
t
lead
t
o
s
ev
er
e
i
m
p
ac
ts
o
n
th
e
h
ea
lth
i
n
th
e
later
s
tag
es
o
f
life
.
Of
ten
o
n
e
m
etab
o
lic
d
is
o
r
d
er
lead
to
o
th
er
d
is
o
r
d
er
s
a
n
d
c
an
h
av
e
m
u
ltio
r
g
an
im
p
ac
ts
.
No
n
-
alco
h
o
lic
f
atty
liv
er
d
is
ea
s
e
(
NAFL
D)
is
o
n
e
o
f
th
e
co
m
p
lex
m
eta
b
o
lic
ch
r
o
n
ic
d
is
o
r
d
er
th
at
h
as
r
ec
en
tly
s
ee
n
a
s
u
r
g
e.
T
h
e
d
is
ea
s
e
is
co
u
p
led
with
o
th
er
m
etab
o
lic
d
is
o
r
d
er
s
as we
ll su
ch
as ty
p
e
2
d
iab
etes m
ellitu
s
an
d
o
b
esit
y
[
2
]
.
NAFL
D
co
n
d
itio
n
in
a
h
u
m
an
b
ein
g
is
in
d
icate
d
b
y
th
e
b
u
il
d
-
up
o
f
ex
ce
s
s
iv
e
f
at
co
n
ten
t
in
th
e
liv
er
o
f
th
o
s
e
in
d
iv
id
u
als
wh
o
ar
e
n
o
t
co
n
s
u
m
in
g
alco
h
o
l
s
ig
n
if
ican
tly
.
T
h
e
co
m
p
lex
ity
o
f
NAFL
D
lies
with
th
e
in
f
lu
en
c
e
o
f
m
u
ltifa
cto
r
ial
im
p
ac
ts
in
th
e
lig
h
t
o
f
m
u
ltip
le
g
en
es
co
m
in
g
to
g
eth
er
in
r
esp
ec
t
to
m
an
y
en
v
ir
o
n
m
e
n
tal
f
ac
to
r
s
.
I
t
is
d
i
f
f
icu
lt
to
id
en
ti
f
y
an
d
tr
ea
t
s
u
c
h
m
u
ltifa
cto
r
i
al
d
is
ea
s
es
as
s
p
ec
if
ic
f
ac
to
r
s
wh
ich
lead
to
s
u
ch
d
is
ea
s
es a
r
e
s
til
l u
n
d
er
th
e
wr
a
p
f
o
r
m
ed
ical
r
esear
ch
e
r
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
en
h
a
n
ce
d
p
r
ed
ictive
mo
d
el
lin
g
fr
a
mewo
r
k
fo
r
h
ig
h
ly
a
cc
u
r
a
te
…
(
N
id
h
i A
r
o
r
a
)
215
Me
d
ical
in
f
o
r
m
atics,
is
an
in
ter
d
is
cip
lin
ar
y
f
ield
o
f
r
esear
ch
wh
ich
is
f
o
cu
s
ed
o
n
ap
p
l
icatio
n
o
f
v
ar
ied
in
f
o
r
m
atio
n
tech
n
o
lo
g
y
d
er
iv
e
n
ar
tific
ial
ly
in
tellig
e
n
t
m
eth
o
d
o
lo
g
ies
f
o
r
th
e
d
iag
n
o
s
is
an
d
tr
ea
tm
en
t
o
f
d
is
ea
s
es
[
3
]
,
[
4
]
.
T
h
e
f
ield
h
as
g
ar
n
er
e
d
m
u
c
h
atten
tio
n
in
th
e
r
esear
ch
s
p
ec
tr
u
m
o
f
m
ed
ical
as
well
as
co
m
p
u
ter
s
cien
ce
p
r
o
f
ess
io
n
a
ls
.
W
ith
th
e
r
is
e
in
th
e
a
v
ailab
ilit
y
o
f
s
u
b
s
tan
tial
m
ed
ical
i
n
f
o
r
m
atio
n
d
u
e
to
in
f
o
r
m
atio
n
tech
n
o
l
o
g
y
ad
v
a
n
ce
m
en
ts
,
r
esear
ch
er
s
ar
e
q
u
ite
in
tellig
en
tly
ass
es
s
in
g
th
is
in
f
o
r
m
atio
n
t
o
s
u
p
p
o
r
t
d
ec
is
io
n
m
ak
in
g
f
o
r
h
ea
lth
p
r
o
f
ess
io
n
als
b
y
ap
p
li
ca
tio
n
o
f
v
a
r
ied
d
ata
an
al
y
tics
,
d
ata
m
in
in
g
an
d
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
u
n
d
er
t
h
e
u
m
b
r
ella
o
f
ar
tifi
cial
in
tellig
en
ce
(
AI
)
.
Of
m
a
n
y
AI
tech
n
i
q
u
es,
m
ac
h
in
e
lear
n
in
g
a
n
d
p
r
ed
icti
v
e
m
o
d
ellin
g
h
as
g
ar
n
e
r
ed
m
u
ch
atten
tio
n
o
f
r
esear
ch
er
s
o
f
l
ate
[
5
]
i
n
th
is
f
ield
.
Ma
ch
in
e
lear
n
in
g
f
o
cu
s
o
n
u
t
ilizin
g
av
ailab
le
m
ed
ical
d
ata
o
f
p
atien
ts
s
u
ch
as
m
ed
ical
r
ec
o
r
d
s
,
s
ig
n
if
ican
t
test
r
esu
lts
,
an
d
m
ed
ical
p
r
es
cr
ip
tio
n
s
.
f
o
r
m
a
k
in
g
m
ac
h
i
n
es
l
ea
r
n
s
ig
n
if
ican
t
p
atter
n
s
an
d
d
ev
elo
p
its
o
wn
p
r
ed
ictio
n
m
o
d
els.
Su
ch
p
r
ed
ictio
n
m
o
d
els
ca
n
th
en
b
e
u
tili
ze
d
f
o
r
au
to
m
atic
p
r
ed
ictio
n
o
f
m
an
y
d
is
ea
s
es
q
u
ite
ea
r
ly
.
Su
ch
tech
n
iq
u
es
a
n
d
th
ei
r
u
s
ef
u
ln
ess
ca
n
b
e
s
u
p
er
b
e
n
ef
icial
f
o
r
tim
ely
p
r
ed
i
ctio
n
o
f
p
o
s
s
ib
ilit
y
o
f
m
etab
o
lic
d
is
o
r
d
e
r
s
,
f
o
r
w
h
ich
o
b
s
er
v
ab
le
h
ea
lth
in
d
icat
o
r
s
ap
p
ea
r
q
u
ite
lately
in
p
ati
en
t
’
s
life
.
Ma
ch
in
e
lear
n
in
g
b
ased
p
r
ed
ictiv
e
a
n
al
y
s
is
b
y
tr
ain
in
g
class
if
icatio
n
an
d
r
eg
r
ess
io
n
m
o
d
els
h
as
b
e
en
d
o
n
e
f
o
r
v
ar
ied
d
is
ea
s
es
s
u
ch
as
d
iab
etes,
h
ea
r
t
d
is
ea
s
es,
liv
er
d
is
ea
s
es
to
n
am
e
a
f
ew
[
6
]
,
[
7
]
.
Ho
wev
er
,
th
e
tr
ain
in
g
o
f
s
u
ch
p
r
ed
ictiv
e
m
o
d
els
an
d
ac
cu
r
a
cy
o
f
p
r
ed
ictio
n
r
esu
lts
lar
g
ely
d
ep
en
d
s
o
n
th
e
q
u
ality
an
d
q
u
an
tity
o
f
d
ata
av
ailab
le
f
o
r
tr
ai
n
in
g
a
n
d
test
in
g
o
f
p
r
ed
ictio
n
m
o
d
els.
Dis
ea
s
e
s
p
ec
if
ic
ap
p
licatio
n
o
f
ch
o
s
en
m
ac
h
i
n
e
lear
n
in
g
tech
n
iq
u
es
h
av
e
b
ee
n
tr
ied
a
n
d
ev
alu
ate
d
b
y
m
a
n
y
r
esear
ch
er
s
in
r
e
ce
n
t
tim
es.
A
d
e
d
icate
d
s
tu
d
y
f
o
r
p
r
e
d
ictio
n
o
f
ca
r
d
io
v
as
cu
lar
d
is
ea
s
es
was
co
n
d
u
cte
d
b
y
Kr
ittan
awo
n
g
et
a
l.
[
8
]
.
T
h
e
s
tu
d
y
o
u
tlin
ed
th
e
im
p
o
r
tan
ce
o
f
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVM
)
an
d
b
o
o
s
tin
g
alg
o
r
ith
m
s
in
p
r
ed
ictio
n
o
f
th
e
c
o
n
ce
r
n
ed
d
is
ea
s
es
with
h
ig
h
er
AUC
m
etr
ic
r
esu
lts
.
Hy
b
r
id
ized
m
ac
h
in
e
lear
n
i
n
g
alg
o
r
ith
m
s
an
d
th
eir
ef
f
ec
tiv
e
n
ess
in
p
r
ed
ictio
n
o
f
h
ea
r
t
d
is
ea
s
es
h
av
e
b
ee
n
d
o
n
e
b
y
Mo
h
an
et
a
l.
[
9
]
.
T
h
e
au
th
o
r
s
p
r
esen
ted
th
e
r
esu
l
ts
o
f
a
n
e
w
p
r
ed
ictio
n
m
o
d
el
wh
ich
was
a
h
y
b
r
id
r
a
n
d
o
m
f
o
r
est
with
a
lin
ea
r
m
o
d
el
(
HR
FLM
)
with
an
ac
cu
r
ac
y
o
f
8
8
.
7
%.
Ma
n
y
o
th
er
r
esear
ch
er
s
[
1
0
]
,
[
1
1
]
also
ev
alu
ated
p
r
ed
ictio
n
m
o
d
els
f
o
r
h
ea
r
t
d
is
ea
s
es
u
s
in
g
v
ar
ie
d
m
ac
h
in
e
lear
n
in
g
tec
h
n
iq
u
es
o
n
d
if
f
er
en
t
s
am
p
le
m
ed
ical
d
atasets
.
A
n
o
t
h
e
r
c
a
t
e
g
o
r
y
o
f
d
i
s
e
a
s
e
s
i
s
n
e
u
r
o
g
e
n
e
r
a
t
i
v
e
,
f
o
r
w
h
i
c
h
s
o
m
e
l
a
t
e
s
t
s
t
u
d
i
e
s
c
o
n
d
u
c
t
e
d
b
y
[
1
2
]
,
[
1
3
]
h
av
e
s
h
o
wn
u
tili
za
tio
n
o
f
m
a
ch
in
e
le
ar
n
in
g
b
ased
p
r
ed
icti
v
e
m
eth
o
d
o
lo
g
ies
to
d
e
v
elo
p
p
r
ed
ictio
n
m
o
d
els.
Pre
d
ictio
n
m
o
d
els
d
ev
elo
p
e
d
f
o
r
R
h
eu
m
atic
d
i
s
ea
s
es
h
av
e
b
ee
n
ex
p
lo
r
e
d
b
y
[
1
4
]
,
[
1
5
]
.
I
n
r
ec
en
t
tim
es,
d
ev
elo
p
in
g
p
r
ed
ictio
n
m
o
d
els
f
o
r
ch
r
o
n
ic
a
n
d
m
etab
o
lic
d
is
o
r
d
er
s
h
av
e
also
g
a
r
n
er
e
d
m
u
ch
atten
tio
n
.
I
n
o
th
er
r
esear
ch
,
Nu
s
in
o
v
ici
et
a
l.
[
1
6
]
also
ass
ess
ed
th
e
f
u
n
cti
o
n
in
g
o
f
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
f
o
r
t
h
e
r
is
k
p
r
ed
ictio
n
o
f
h
ea
r
t
(
ca
r
d
io
v
as
cu
lar
)
d
is
ea
s
es,
k
id
n
ey
d
is
ea
s
e,
h
y
p
er
ten
s
io
n
an
d
d
iab
etes
u
s
in
g
s
im
p
le
clin
ical
p
r
ed
icto
r
s
.
Ma
n
y
o
t
h
er
s
tu
d
ie
s
co
n
d
u
cted
b
y
v
ar
io
u
s
r
esear
ch
er
s
f
o
r
ch
r
o
n
ic
a
n
d
m
etab
o
lic
d
is
ea
s
es
h
av
e
b
ee
n
d
o
n
e
r
ec
e
n
tly
u
s
in
g
v
ar
ie
d
m
ac
h
in
e
lear
n
in
g
class
if
icatio
n
alg
o
r
ith
m
s
.
An
o
th
er
m
etab
o
lic
d
is
ea
s
e
wh
ich
h
as
g
ar
n
e
r
ed
atte
n
tio
n
o
f
r
esear
ch
er
s
in
m
e
d
ical
in
f
o
r
m
atics
is
NAFL
D
d
is
ea
s
e.
NAFL
D
d
is
ea
s
e
m
ay
lead
to
o
th
er
m
eta
b
o
lic
d
is
ea
s
es
s
u
c
h
as
ca
r
d
io
v
a
s
cu
lar
d
is
ea
s
es
[
1
7
]
an
d
g
en
e
r
ate
m
an
y
o
th
er
h
ea
l
th
r
is
k
s
.
AI
tech
n
iq
u
es
in
clu
d
i
n
g
m
ac
h
in
e
lear
n
in
g
s
u
c
h
as
class
if
icatio
n
u
s
in
g
lo
g
is
tic
r
eg
r
ess
io
n
,
r
an
d
o
m
f
o
r
est
,
XGBo
o
s
t
an
d
d
ec
is
io
n
tr
ee
ar
e
a
p
p
lied
f
o
r
d
etec
tin
g
th
is
d
is
ea
s
e
b
y
r
esear
ch
er
s
as
p
r
esen
ted
b
y
W
o
n
g
et
a
l.
[
1
8
]
.
T
h
e
a
p
p
lie
d
tech
n
iq
u
es
u
s
ed
d
atasets
o
f
elec
tr
o
n
ically
s
to
r
ed
h
ea
lth
r
ec
o
r
d
s
o
f
in
d
iv
id
u
als,
B
io
p
s
y
r
ec
o
r
d
s
o
f
l
iv
er
,
alo
n
g
with
l
iv
er
im
ag
es.
Var
io
u
s
o
th
er
r
esear
ch
er
s
h
av
e
also
u
s
ed
clin
ical
o
b
s
er
v
an
t
p
ar
am
eter
s
-
b
ased
d
ataset
f
o
r
d
ev
elo
p
in
g
m
ac
h
in
e
lear
n
in
g
mode
ls
a
n
d
p
r
ed
ict
NAFL
D
d
is
ea
s
e
[
1
9
]
,
[
2
0
]
.
T
h
e
ac
cu
r
ac
y
r
esu
lts
as
d
is
c
u
s
s
ed
in
ab
o
v
e
s
tu
d
ies
ar
e
v
ar
ied
f
o
r
d
if
f
er
e
n
t
m
ac
h
in
e
lear
n
in
g
m
o
d
els.
T
h
e
r
esu
lts
r
ep
o
r
ted
ar
e
en
lig
h
ten
in
g
h
o
wev
er
it
is
ev
id
e
n
t
th
at
n
o
t
m
u
ch
a
n
aly
s
is
is
d
o
n
e
r
eg
a
r
d
in
g
t
h
e
s
ig
n
if
ica
n
ce
o
f
p
r
o
ce
s
s
in
g
o
f
d
atasets
to
im
p
r
o
v
e
its
q
u
ality
as a
n
im
p
o
r
tan
t step
p
r
io
r
to
d
ev
elo
p
m
e
n
t o
f
m
ac
h
in
e
lear
n
in
g
p
r
e
d
ictio
n
m
o
d
els f
o
r
p
r
o
g
n
o
s
is
o
f
NAFL
D
d
is
ea
s
es.
T
h
e
cu
r
r
en
t
r
esear
ch
s
u
r
g
e
i
n
th
e
p
r
e
d
ictio
n
o
f
m
eta
b
o
lic
a
n
d
ch
r
o
n
ic
d
is
ea
s
es
is
clea
r
ly
v
is
ib
le
d
u
e
to
h
ig
h
h
ea
lth
im
p
ac
ts
o
f
s
u
ch
d
is
ea
s
es.
Ho
wev
er
,
an
aly
zin
g
av
ailab
le
d
ata
s
ets
p
r
io
r
to
d
ev
elo
p
m
e
n
t
o
f
p
r
ed
ictiv
e
m
o
d
els
h
av
e
n
o
t
b
e
en
d
o
n
e
in
d
e
p
th
.
Su
c
h
p
r
e
p
r
o
ce
s
s
in
g
f
o
r
q
u
ality
im
p
r
o
v
em
e
n
ts
o
f
th
e
av
ai
lab
l
e
d
atasets
ca
n
h
av
e
a
s
ig
n
if
ican
t
im
p
ac
t
o
f
tr
ain
in
g
p
r
ed
ictio
n
m
o
d
els
in
b
r
o
a
d
r
an
g
es
o
f
m
a
ch
in
e
lear
n
in
g
a
n
d
AI
o
n
a
wh
o
le.
T
h
er
ef
o
r
e
,
th
is
p
ap
er
p
r
esen
ts
a
co
m
p
lete
f
r
am
ewo
r
k
f
o
r
p
r
ep
r
o
ce
s
s
in
g
f
o
r
q
u
ality
im
p
r
o
v
em
e
n
t
o
f
m
ed
ical
d
atas
ets
an
d
th
en
ev
a
l
u
atin
g
th
ese
h
ig
h
-
q
u
ality
d
ata
s
ets
in
d
ev
el
o
p
m
en
t
o
f
m
ac
h
i
n
e
lear
n
in
g
tr
ain
ed
h
ig
h
ly
q
u
al
itativ
e
p
r
ed
ictio
n
m
o
d
els.
Var
ied
m
eth
o
d
o
l
o
g
ies
ar
e
u
tili
ze
d
f
o
r
q
u
ality
im
p
r
o
v
em
e
n
ts
an
d
th
e
n
th
e
im
p
r
o
v
e
d
d
ataset
is
em
p
lo
y
e
d
f
o
r
tr
ain
in
g
o
f
m
ac
h
in
e
lear
n
in
g
m
o
d
e
ls
.
T
h
e
p
ap
e
r
p
er
f
o
r
m
s
in
-
d
ep
th
ex
p
er
im
en
t
al
ev
alu
atio
n
s
o
f
tr
ain
in
g
an
d
test
in
g
ac
cu
r
ac
ies
o
f
s
ev
en
p
r
ev
elan
t
m
ac
h
in
e
lear
n
in
g
m
o
d
els.
T
h
e
co
n
d
u
c
ted
s
tu
d
ies
h
av
e
s
tr
en
g
th
en
ed
th
e
f
ac
t
th
at
p
r
ep
r
o
ce
s
s
in
g
o
f
d
atasets
p
lay
s
a
s
ig
n
if
ican
t r
o
le
in
n
o
t
o
n
ly
im
p
r
o
v
in
g
ac
cu
r
ac
ies b
u
t a
ls
o
im
p
r
o
v
in
g
r
esu
lts
o
f
o
th
e
r
m
etr
ic
s
s
u
ch
as AU
C
an
d
F1
-
s
co
r
e
.
R
esear
ch
g
ap
an
d
m
ain
co
n
tr
ib
u
tio
n
:
av
ailab
ilit
y
o
f
q
u
ality
d
ata
s
ets
i
s
q
u
ite
an
ess
en
tia
l
r
eq
u
ir
em
e
n
t
f
o
r
tr
ain
in
g
o
f
p
r
ed
ictio
n
m
o
d
els.
Ho
wev
er
,
in
m
ed
ical
ec
o
s
y
s
tem
s
,
d
ata
is
en
o
r
m
o
u
s
ly
g
en
er
ated
o
n
a
r
eg
u
lar
b
asis
b
u
t
p
r
im
ar
ily
r
etain
e
d
in
r
aw
an
d
u
n
p
r
o
ce
s
s
ed
f
o
r
m
[
2
1
]
.
Mo
r
e
s
o
,
a
c
o
m
m
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
2
1
4
-
2
2
2
216
f
r
am
ewo
r
k
is
r
eq
u
ir
e
d
to
s
to
r
e
p
atien
t
id
in
d
e
x
ed
m
e
d
ical
d
a
tasets
in
a
co
m
m
o
n
s
er
v
er
lin
k
in
g
all
th
e
m
ed
ical
h
o
s
p
itals
th
r
o
u
g
h
o
u
t
as
p
r
o
p
o
s
ed
b
y
Ar
o
r
a
et
a
l.
[
2
2
]
.
Data
p
r
e
p
r
o
ce
s
s
in
g
,
an
im
p
o
r
tan
t
in
g
r
e
d
ien
t
o
f
th
is
f
r
am
ewo
r
k
,
h
as
to
b
e
ass
ess
e
d
f
o
r
m
e
d
ical
d
ata
s
ets
an
d
co
m
m
o
n
p
o
licies
f
o
r
p
r
e
p
r
o
ce
s
s
in
g
m
ed
ical
d
ata
t
o
im
p
r
o
v
e
q
u
alit
y
f
o
r
d
ev
elo
p
i
n
g
h
ig
h
ly
ef
f
icien
t
p
r
e
d
ictio
n
m
o
d
els
is
r
eq
u
ir
ed
.
T
h
is
p
ap
er
e
x
p
lo
r
es
an
d
p
r
esen
ts
v
ar
ied
d
ata
p
r
ep
r
o
c
ess
in
g
-
b
ased
m
eth
o
d
o
lo
g
ies
f
o
r
m
e
d
ical
d
ata
to
p
r
ed
ict
NAFL
D
m
etab
o
lic
d
is
o
r
d
er
.
T
h
e
m
et
h
o
d
o
lo
g
ies
ap
p
lied
h
av
e
s
u
cc
ess
f
u
lly
im
p
r
o
v
e
d
n
o
t
o
n
l
y
th
e
ac
cu
r
ac
y
o
f
th
e
p
r
e
d
ictio
n
m
o
d
els
b
u
t
also
th
e
p
r
ec
is
io
n
o
f
t
h
e
tr
ain
e
d
m
o
d
el.
Var
ied
tech
n
iq
u
es
f
o
r
d
ata
q
u
ality
i
m
p
r
o
v
e
m
en
t
h
av
e
b
ee
n
r
ig
o
r
o
u
s
ly
ap
p
lied
an
d
r
esu
lts
p
r
esen
ted
in
th
is
p
ap
e
r
wh
ich
ca
n
b
e
u
s
ed
in
th
e
m
ed
ical
in
f
o
r
m
atics.
T
r
ain
in
g
an
d
test
in
g
d
ata
p
r
ed
ictio
n
r
esu
lts
o
n
v
ar
ie
d
p
r
ed
ictio
n
q
u
ality
q
u
an
tific
a
tio
n
m
etr
ics
s
u
c
h
“
ac
cu
r
ac
y
”
,
“
p
r
ec
is
io
n
”
,
“
r
ec
all
”
an
d
“
F1
-
s
co
r
e
”
u
s
in
g
u
n
p
r
o
ce
s
s
ed
d
ata
a
n
d
p
r
o
ce
s
s
ed
d
ata
h
as
b
ee
n
d
o
cu
m
e
n
ted
f
o
r
s
ev
en
d
if
f
er
e
n
t
s
tate
o
f
th
e
ar
t
m
ac
h
in
e
le
ar
n
in
g
b
ased
p
r
e
d
ictiv
e
m
o
d
e
ls
n
am
ed
“
lo
g
is
tic
r
eg
r
ess
io
n
”
,
“
Naïv
e
B
ay
es
”
,
“
SVM
”
,
“
d
ec
is
io
n
tr
ee
”
,
“
n
eu
r
al
n
etwo
r
k
”
,
“
r
a
n
d
o
m
f
o
r
est
”
an
d
“
KNN
”
.
Var
ied
p
y
th
o
n
-
b
ased
u
tili
ties
to
au
t
o
m
ate
th
e
q
u
ality
en
h
a
n
ce
m
en
t
p
r
o
ce
s
s
h
av
e
b
ee
n
lis
ted
s
u
c
h
as
u
s
e
o
f
p
y
th
o
n
im
p
u
te
r
an
d
p
y
th
o
n
s
m
o
te
u
til
ity
to
en
h
an
ce
a
n
d
b
alan
ce
t
h
e
d
ata
s
ets
in
ca
s
e
o
f
im
b
alan
ce
class
d
is
tr
ib
u
tio
n
f
o
r
q
u
ality
en
h
a
n
ce
m
en
ts
an
d
r
ea
lis
tic
p
r
ed
ictio
n
s
u
s
in
g
eq
u
al
d
is
tr
ib
u
tio
n
o
f
class
d
ata
s
ets.
2.
M
E
T
H
O
D
C
lin
ical
o
b
s
er
v
atio
n
s
th
o
u
g
h
ar
e
n
o
t
d
ir
ec
tly
in
d
icativ
e
o
f
NAFL
D,
b
u
t
if
s
u
ch
o
b
s
er
v
atio
n
s
ar
e
r
ec
o
r
d
e
d
o
v
er
tim
e
with
t
h
eir
p
r
ed
ictio
n
o
f
NAFL
D
s
tatu
s
o
f
d
ia
g
n
o
s
ed
p
atien
ts
,
th
e
n
s
u
ch
a
d
ata
ca
n
ce
r
tain
ly
b
e
u
tili
ze
d
as
class
if
ied
d
ata
f
o
r
tr
ain
in
g
m
ac
h
in
e
lear
n
in
g
p
r
ed
ictiv
e
m
o
d
els.
Ho
wev
er
,
s
in
ce
t
h
e
clin
ical
o
b
s
er
v
atio
n
s
ar
e
p
r
im
ar
ily
r
ec
o
r
d
ed
m
a
n
u
ally
a
n
d
lar
g
ely
d
ep
en
d
s
o
n
m
ed
ic
al
ex
p
er
ts
;
th
e
d
ata
g
en
er
ally
s
u
f
f
er
s
f
r
o
m
in
c
o
m
p
leten
ess
;
r
ed
u
n
d
a
n
cies;
u
n
eq
u
al
class
d
is
tr
ib
u
tio
n
s
an
d
m
u
ltip
le
co
lu
m
n
s
o
f
clin
ical
v
ar
iab
les
wh
ich
ar
e
h
i
g
h
ly
co
r
r
elate
d
.
Data
s
et
with
s
u
ch
p
r
o
p
er
ties
;
m
ay
b
eh
a
v
e
i
n
co
n
s
is
ten
tly
o
n
ce
s
tatis
t
ically
u
tili
ze
d
f
o
r
tr
ai
n
in
g
m
ac
h
in
e
lear
n
i
n
g
p
r
ed
ictiv
e
an
aly
s
is
.
T
h
e
p
r
im
ar
y
o
b
jectiv
e
o
f
th
is
co
n
d
u
cte
d
r
esear
ch
w
o
r
k
is
t
o
ex
am
in
e
an
d
u
tili
ze
d
ata
p
r
ep
r
o
ce
s
s
in
g
tech
n
iq
u
es
p
r
i
o
r
to
ap
p
licatio
n
o
f
m
o
d
el
tr
ain
in
g
p
h
ase
as
a
co
m
p
u
ls
o
r
y
s
tep
in
d
ev
elo
p
m
en
t
o
f
tr
ain
ed
p
r
ed
ictio
n
m
o
d
el
s
o
f
m
etab
o
lic
an
d
ch
r
o
n
ic
d
is
o
r
d
e
r
s
.
T
h
e
m
eth
o
d
o
lo
g
y
f
o
r
th
e
c
o
n
d
u
cted
r
esear
ch
wo
r
k
s
to
war
d
s
g
e
n
er
atin
g
h
ig
h
ly
q
u
alitativ
e,
clea
n
an
d
ev
e
n
ly
d
is
tr
ib
u
te
d
d
ata
f
o
r
d
ev
elo
p
in
g
q
u
al
itativ
e
p
r
ed
ictiv
e
m
o
d
els,
wh
ich
r
ep
o
r
t
h
ig
h
p
er
f
o
r
m
an
ce
lev
els
in
ter
m
s
o
f
ac
cu
r
a
cy
,
p
r
ec
ess
io
n
,
r
ec
all
,
F1
-
s
co
r
e
,
an
d
AUC
p
r
e
d
ictio
n
q
u
ality
q
u
an
tifie
r
m
etr
ics.
T
h
e
id
eo
lo
g
y
is
n
o
t
o
n
ly
to
im
p
r
o
v
e
ac
c
u
r
ac
y
b
u
t
a
ls
o
to
im
p
r
o
v
e
p
r
ec
is
io
n
v
al
u
e
s
an
d
AUC
r
esu
lts
,
wh
ich
is
a
s
ig
n
if
ican
t
i
n
d
icat
o
r
o
f
h
ig
h
ly
ac
c
u
r
ate
p
r
ed
icti
o
n
.
T
h
e
m
eth
o
d
o
lo
g
y
ad
ap
te
d
f
o
r
th
e
c
o
n
d
u
cted
r
es
ea
r
ch
wo
r
k
is
d
ep
icted
u
s
i
n
g
a
f
r
am
ewo
r
k
as
s
h
o
w
n
u
s
i
n
g
p
h
ase
d
iag
r
a
m
in
Fig
u
r
e
1
.
T
h
e
b
r
o
ad
s
tep
s
as
s
h
o
wn
in
ab
o
v
e
p
h
ase
d
iag
r
a
m
ar
e
ex
p
lain
e
d
in
Fig
u
r
e
1
.
−
Step
1
.
D
ata
s
e
t
g
en
er
atio
n
o
f
NAFL
D
d
is
ea
s
e:
a
s
a
f
ir
s
t
s
t
ep
in
th
e
s
u
g
g
ested
p
h
ased
d
i
ag
r
am
,
clin
ical
o
b
s
er
v
atio
n
s
f
r
o
m
d
if
f
er
en
t
m
ed
ical
s
o
u
r
ce
s
a
r
e
g
ath
er
ed
an
d
m
er
g
ed
to
g
eth
e
r
to
f
o
r
m
a
s
in
g
le
r
e
p
o
s
ito
r
y
o
f
a
NAFL
D
d
is
ea
s
e.
Fo
r
o
u
r
co
n
d
u
cted
s
tu
d
y
,
a
clin
ic
al
o
b
s
er
v
atio
n
s
d
ataset
o
f
1
7
5
4
9
in
d
iv
id
u
als
m
er
g
ed
f
r
o
m
d
if
f
er
e
n
t
s
o
u
r
ce
s
av
ailab
le
o
n
v
in
ce
n
tar
elb
u
n
d
o
ck
.
g
it
h
u
b
.
i
o
/R
d
atasets
/d
atas
ets.h
tm
l
is
u
s
ed
in
th
e
co
n
d
u
cte
d
s
tu
d
y
.
Fo
r
s
e
v
en
attr
ib
u
tes
r
ec
o
r
d
ed
(
id
attr
ib
u
te
is
ir
r
elev
an
t)
an
d
av
aila
b
le
o
n
p
latf
o
r
m
is
u
s
ed
in
th
e
co
n
d
u
cted
s
tu
d
y
.
A
s
n
ap
s
h
o
t o
f
t
h
e
d
ataset
is
s
h
o
wn
in
Fig
u
r
e
2
.
T
h
e
p
r
im
ar
y
r
ef
e
r
en
ce
f
o
r
th
e
d
ata
s
et
s
h
o
wn
a
b
o
v
e
f
o
r
N
AFLD
r
o
o
ts
b
ac
k
to
th
e
s
tu
d
y
co
n
d
u
cted
by
Allen
et
a
l.
[
2
3
]
.
T
h
e
a
u
th
o
r
d
ev
is
ed
a
p
o
p
u
latio
n
co
h
o
r
t
co
n
s
is
tin
g
o
f
th
e
d
ata
co
l
lecte
d
f
o
r
all
a
d
u
lt
NAFL
D
p
r
o
s
p
ec
tiv
e
p
atien
ts
f
r
o
m
y
ea
r
s
s
p
an
n
in
g
in
t
h
e
r
a
n
g
e
o
f
1
9
9
7
to
2
0
1
4
.
T
h
e
s
n
a
p
s
h
o
t
s
h
o
wn
ab
o
v
e
is
r
eg
en
er
ated
s
u
c
h
th
at
all
th
e
co
lu
m
n
s
’
d
ata
in
th
e
o
r
ig
in
al
s
tu
d
y
ar
e
r
em
ap
p
ed
to
h
id
e
a
n
d
p
r
o
tect
p
atien
t
’
s
co
n
f
id
en
tiality
.
Patien
t
’
s
ag
e
r
ep
r
esen
ted
in
th
e
Fig
u
r
e
2
is
th
e
n
u
m
er
ic
a
g
e
at
th
e
d
ate
o
f
in
d
ex
in
g
,
a
n
d
th
e
s
u
b
ject
id
en
tifie
r
is
a
r
an
d
o
m
n
u
m
b
er
.
As
a
f
in
al
d
ata
p
r
o
tectio
n
f
o
r
i
n
d
iv
id
u
als,
th
e
d
ataset
s
h
o
wn
a
b
o
v
e
an
d
u
tili
ze
d
in
o
u
r
co
n
d
u
cted
s
tu
d
y
u
s
es
o
n
ly
a
p
p
r
o
x
im
ately
9
0
%
r
an
d
o
m
ly
p
ick
ed
d
ata
f
r
o
m
th
e
o
r
ig
in
al
d
ata
o
f
th
e
au
th
o
r
s
o
f
th
e
p
r
im
a
r
y
s
tu
d
y
.
T
h
e
d
escr
ip
tio
n
o
f
th
e
v
a
r
iab
le
n
am
es
u
s
ed
in
th
e
d
ata
s
et
ar
e
as
f
o
llo
ws:
‘
id
’
is
th
e
s
u
b
ject
’
s
(
i
n
d
iv
id
u
al
’
s
)
id
en
tifie
r
;
‘
ag
e
’
is
th
e
a
g
e
at
d
ate
o
f
in
d
ex
in
g
to
th
e
co
n
d
u
cted
s
tu
d
y
;
‘
m
ale
’
v
ar
iab
le
s
to
r
es
v
alu
e
‘
0
’
f
o
r
r
e
p
r
esen
tin
g
f
em
ales
an
d
1
o
th
er
wis
e;
‘
weig
h
t
’
r
ep
r
esen
ts
weig
h
t
o
f
th
e
s
u
b
ject
in
k
ilo
g
r
am
s
;
‘
h
eig
h
t
’
co
lu
m
n
s
to
r
es
th
e
h
eig
h
t
o
f
th
e
s
u
b
ject
u
n
d
er
s
tu
d
y
in
ce
n
ti
m
eter
s
;
‘
bmi
’
is
th
e
b
o
d
y
m
ass
in
d
ex
o
f
th
e
s
u
b
jec
t;
‘
ca
s
e.
id
’
is
th
e
id
n
u
m
b
er
o
f
th
e
NAFL
D
ca
s
e
with
wh
ich
s
u
b
ject
u
n
d
er
s
tu
d
y
g
ets
m
atch
ed
;
‘
f
u
tim
e
’
is
th
e
tim
e
to
d
ea
th
o
r
last
f
o
llo
w
-
u
p
o
f
th
e
s
u
b
ject;
‘
s
tatu
s
’
is
0
if
th
e
s
u
b
ject
was
aliv
e
at
th
e
last
f
o
llo
w
-
u
p
else 1
if
th
e
s
u
b
ject
was d
ea
d
.
−
Step
2
.
M
is
s
in
g
d
ata
am
p
u
tati
o
n
s
:
t
h
e
d
ata
s
n
ap
s
h
o
t
d
ep
icte
d
in
Fig
u
r
e
2
d
is
p
lay
s
th
e
p
r
es
en
ce
o
f
m
is
s
in
g
d
ata
v
alu
es
in
t
h
e
r
ec
o
r
d
ed
o
b
s
er
v
atio
n
s
o
f
in
d
i
v
id
u
als
r
ep
r
esen
ted
as
‘
NAN
’
in
n
u
m
er
ical
co
lu
m
n
s
(
‘
weig
h
t
’
,
h
eig
h
t
’
,
‘
b
m
i
’
)
.
D
ata
h
av
in
g
m
is
s
in
g
v
alu
es,
is
n
o
t
s
u
itab
le
f
o
r
s
tatis
tical
an
aly
s
is
n
o
r
f
o
r
m
ac
h
in
e
lear
n
in
g
p
r
ed
ictiv
e
m
o
d
ellin
g
.
Hen
ce
,
s
u
c
h
v
alu
e
s
n
ee
d
cr
itical
an
al
y
s
is
an
d
a
m
p
u
tatio
n
s
u
s
in
g
s
u
itab
le
m
eth
o
d
o
lo
g
ies.
Fo
r
o
u
r
co
n
d
u
cted
s
tu
d
y
,
m
is
s
in
g
v
alu
es in
th
e
d
atasets
ar
e
m
ea
n
r
ep
lace
d
u
s
in
g
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
en
h
a
n
ce
d
p
r
ed
ictive
mo
d
el
lin
g
fr
a
mewo
r
k
fo
r
h
ig
h
ly
a
cc
u
r
a
te
…
(
N
id
h
i A
r
o
r
a
)
217
Simp
leI
m
p
u
ter
u
tili
ty
f
r
o
m
s
k
lear
n
.
im
p
u
te
p
ac
k
ag
e
o
f
p
y
t
h
o
n
[
2
4
]
.
T
h
e
c
o
r
r
ec
ted
d
ata
s
et
s
n
ap
s
h
o
t
b
y
m
ea
n
r
ep
lace
m
e
n
t u
s
in
g
a
b
o
v
e
p
y
th
o
n
u
til
ity
f
o
r
n
u
m
er
ical
co
lu
m
n
s
‘
NAN
’
v
alu
es is
s
h
o
wn
in
Fig
u
r
e
3
.
−
Step
3
.
D
ata
c
o
r
r
elatio
n
ev
al
u
atio
n
:
p
r
ed
ictiv
e
m
o
d
ellin
g
f
o
r
class
if
icatio
n
o
f
d
e
p
en
d
e
n
t
v
ar
iab
le
(
class
v
ar
iab
le)
h
ig
h
ly
d
ep
e
n
d
s
u
p
o
n
n
u
m
b
e
r
o
f
in
d
e
p
en
d
e
n
t
v
a
r
iab
les
u
s
ed
in
th
e
m
o
d
el
g
e
n
er
atio
n
.
Hig
h
n
u
m
b
er
o
f
v
ar
iab
les
u
s
ed
in
th
e
p
r
ed
ictio
n
m
o
d
el
o
f
ten
lea
d
to
p
r
o
b
lem
o
f
o
v
e
r
f
itti
n
g
wh
ich
lead
to
f
alse
an
d
o
v
er
p
o
s
itiv
e
p
r
ed
ictio
n
s
o
n
tr
ain
in
g
wh
ile
h
av
in
g
v
e
r
y
p
o
o
r
p
er
f
o
r
m
a
n
ce
o
n
test
in
g
d
ataset.
A
q
u
ite
s
im
p
ler
m
eth
o
d
to
h
an
d
le
th
i
s
p
r
o
b
lem
is
to
k
ee
p
m
i
n
im
u
m
in
d
ep
e
n
d
en
t
v
ar
iab
les
in
p
r
ed
ictiv
e
m
o
d
el
g
en
er
atio
n
,
b
y
d
r
o
p
p
in
g
h
ig
h
l
y
co
r
r
elate
d
v
ar
ia
b
les.
Hen
ce
,
a
co
r
r
elatio
n
h
ea
t
m
ap
m
atr
ix
is
g
en
er
ated
as
s
h
o
wn
in
Fig
u
r
e
4
f
o
r
NAFL
D
d
ataset,
wh
ich
clea
r
ly
d
e
p
icts
h
ig
h
co
r
r
elatio
n
b
etwe
en
‘
wei
g
h
t
’
an
d
‘
bmi
’
.
Hen
ce
,
‘
b
m
i
’
is
d
r
o
p
p
ed
f
r
o
m
th
e
d
ataset
to
r
etain
o
n
ly
s
ig
n
if
ican
tly
h
i
g
h
ly
u
n
c
o
r
r
elate
d
f
ea
tu
r
es
wh
ic
h
ca
n
h
av
e
i
n
d
ep
e
n
d
en
t im
p
ac
t
o
n
m
o
d
el
d
ev
el
o
p
m
en
t a
n
d
r
e
d
u
ce
th
e
c
o
m
p
lex
ity
o
f
m
o
d
el.
Fig
u
r
e
1
.
Ph
ase
d
iag
r
am
f
o
r
N
AFLD
d
is
ea
s
e
p
r
ed
ictio
n
u
s
in
g
q
u
alitativ
e
d
ata
Fig
u
r
e
2
.
NAFL
D
d
ataset
s
n
ap
s
h
o
t
Fig
u
r
e
3
.
C
o
r
r
ec
te
d
d
ata
with
m
ea
n
r
ep
lace
m
e
n
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
2
1
4
-
2
2
2
218
Fig
u
r
e
4
.
C
o
r
r
elatio
n
Hea
tm
ap
f
o
r
NAFL
D
d
ataset
−
Step
4
.
C
lass
b
alan
ce
d
is
tr
ib
u
tio
n
ev
alu
atio
n
:
it
is
o
b
s
er
v
ed
in
th
e
NAFL
D
d
ataset
th
at
t
h
e
class
v
ar
iab
le
‘
s
tatu
s
’
h
as
q
u
ite
u
n
eq
u
al
d
is
t
r
ib
u
tio
n
f
o
r
v
alu
es
‘
0
’
an
d
‘
1
’
.
I
t
is
h
av
in
g
m
o
r
e
o
f
‘
1
’
as
c
o
m
p
ar
ed
t
o
‘
0
’
,
wh
ich
m
ak
e
th
e
p
r
ed
ictiv
e
m
o
d
ellin
g
b
iased
f
o
r
class
v
alu
e
‘
1
’
.
Hen
ce
,
to
m
ak
e
th
e
tr
ain
i
n
g
o
f
p
r
ed
ictiv
e
m
o
d
els u
n
b
iased
,
a
n
ec
ess
ar
y
s
tep
to
eq
u
alize
th
e
class
d
i
s
tr
i
b
u
tio
n
,
with
p
er
f
o
r
m
in
g
u
p
/d
o
wn
-
s
am
p
lin
g
is
d
o
n
e.
I
n
u
p
-
s
am
p
lin
g
,
r
o
ws
f
o
r
class
v
alu
e
with
lo
we
r
o
cc
u
r
r
en
ce
a
r
e
a
p
p
en
d
ed
alo
n
g
wit
h
m
ajo
r
ity
class
r
o
ws
in
th
e
d
ataset
with
an
o
v
er
all
d
is
tr
ib
u
tio
n
r
ep
r
esen
tin
g
th
e
o
r
ig
in
al
d
ataset.
T
h
e
d
at
a
ca
n
b
e
u
n
d
er
-
s
am
p
led
with
a
r
ev
er
s
e
p
r
o
ce
d
u
r
e.
Dif
f
er
e
n
t
u
tili
ties
in
p
y
th
o
n
ar
e
av
ailab
le
f
o
r
u
p
-
s
am
p
lin
g
an
d
u
n
d
er
-
s
am
p
lin
g
as
s
h
o
wn
in
b
elo
w
Fig
u
r
e
5
.
Fig
u
r
e
5
(
a)
s
h
o
ws
th
e
u
s
ag
e
o
f
p
y
th
o
n
S
MO
T
E
[
2
5
]
u
tili
ty
to
au
to
m
atica
lly
u
p
-
s
am
p
le
th
e
m
in
o
r
ity
class
.
T
h
is
u
tili
ty
is
u
tili
ze
d
in
o
u
r
c
o
n
d
u
cted
r
ese
ar
ch
wo
r
k
.
Fig
u
r
e
5
(
b
)
s
h
o
ws th
e
d
etails
o
f
d
ataset
h
av
in
g
n
o
w
1
9
0
3
4
t
o
tal
r
o
ws with
o
v
er
s
am
p
le
d
at
a.
(
a)
(
b
)
Fig
u
r
e
5
.
Up
s
am
p
lin
g
o
f
d
ata
f
o
r
h
a
n
d
lin
g
class
im
b
alan
ce
(
a)
u
s
ag
e
o
f
SMOT
E
u
tili
ty
f
o
r
o
v
er
s
am
p
lin
g
o
f
NAFL
D
d
ataset
an
d
(
b
)
u
p
s
ca
led
NAFL
D
d
ataset
d
etails
−
Step
5
.
S
tr
atif
ied
s
am
p
lin
g
:
s
t
r
atif
ied
s
am
p
lin
g
is
an
ess
en
ti
al
s
tep
to
d
iv
id
e
t
h
e
d
ata
s
et
i
n
to
tr
ain
in
g
an
d
test
in
g
d
ata;
s
o
as
to
h
av
e
e
q
u
ally
d
is
tr
ib
u
ted
r
ep
r
esen
tatio
n
o
f
all
th
e
class
es
o
f
d
ep
en
d
en
t
v
ar
iab
le
(
i
n
o
u
r
ca
s
e
its
‘
s
tatu
s
’
)
in
b
o
th
th
e
tr
ain
in
g
as
well
as
te
s
ti
n
g
d
ataset.
T
h
e
s
tr
atif
ied
d
is
tr
ib
u
tio
n
en
s
u
r
es
ju
s
tifie
d
tr
ain
in
g
m
o
d
el
d
e
v
elo
p
m
en
t w
h
ic
h
is
u
n
b
iased
h
av
in
g
r
ea
lis
tic
test
in
g
ac
cu
r
ac
y
r
esu
lts
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
E
x
p
er
im
en
tatio
n
u
s
in
g
th
e
p
r
o
ce
s
s
ed
an
d
u
p
s
ca
led
d
ata
o
f
NAFL
D
b
y
f
o
llo
win
g
th
e
a
b
o
v
e
p
h
ased
p
r
o
ce
d
u
r
e
s
tep
b
y
s
tep
is
d
o
n
e
u
s
in
g
Go
o
g
le
C
o
llab
.
R
esu
l
ts
o
f
p
r
ed
ictio
n
ac
cu
r
ac
y
o
f
t
h
e
tr
ain
ed
m
o
d
el
o
n
3
0
%
test
in
g
d
ataset
i
s
ev
alu
ated
u
s
in
g
n
o
n
-
s
tr
atif
ied
,
s
tr
atif
ied
an
d
u
p
s
ca
led
s
tr
atif
ied
d
ata.
C
o
n
f
u
s
io
n
m
atr
ices
ar
e
g
en
e
r
ated
t
o
q
u
a
n
tify
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
a
ll,
F1
-
s
co
r
e
m
etr
ic
v
alu
es.
T
h
ese
m
etr
ics
ar
e
v
er
y
ap
p
r
o
p
r
iate
in
d
icato
r
s
o
f
q
u
ali
ty
o
f
p
r
ed
ictio
n
s
d
o
n
e
b
y
an
y
p
r
ed
icto
r
m
o
d
els.
R
esu
lts
o
f
p
r
ed
ictio
n
o
f
s
ev
en
p
r
ed
ictiv
e
m
o
d
els
o
n
test
d
at
a
p
r
ed
ictio
n
f
o
r
NAFL
D
d
is
ea
s
e
ar
e
co
llected
a
n
d
a
n
aly
ze
d
in
o
u
r
co
n
d
u
cted
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
en
h
a
n
ce
d
p
r
ed
ictive
mo
d
el
lin
g
fr
a
mewo
r
k
fo
r
h
ig
h
ly
a
cc
u
r
a
te
…
(
N
id
h
i A
r
o
r
a
)
219
r
esear
ch
wo
r
k
.
T
h
e
s
ev
e
n
p
r
e
d
ictiv
e
m
o
d
el
g
en
e
r
atio
n
alg
o
r
ith
m
s
ar
e
lo
g
is
tic
r
eg
r
ess
io
n
,
Naïv
e
B
ay
es,
SVM,
n
eu
r
al
n
etwo
r
k
,
r
a
n
d
o
m
f
o
r
est,
KNN,
an
d
d
ec
is
io
n
tr
ee
.
Par
am
eter
t
u
n
in
g
:
fo
r
o
u
r
c
o
n
d
u
cte
d
ex
p
er
im
en
tatio
n
,
a
s
ig
n
if
ican
t
s
tep
to
tu
n
e
th
e
‘
k
er
n
el
’
p
ar
am
eter
o
f
SVM
m
o
d
el,
‘
n
u
m
b
er
o
f
n
eig
h
b
o
r
s
’
p
ar
a
m
eter
in
KNN
m
o
d
el
an
d
‘
n
u
m
b
er
o
f
esti
m
ato
r
s
’
p
ar
am
eter
s
in
r
an
d
o
m
f
o
r
est
m
o
d
el
is
also
p
er
f
o
r
m
ed
.
T
h
e
r
esu
lts
o
f
ac
cu
r
ac
y
s
co
r
es o
b
ta
in
ed
f
o
r
th
is
s
tep
ar
e
d
ep
icted
u
s
i
n
g
v
ar
io
u
s
p
lo
ts
in
Fig
u
r
e
6
.
I
t
is
o
b
s
er
v
ed
th
at
r
esu
lts
o
f
ac
cu
r
ac
y
wer
e
b
est
at
Po
ly
k
er
n
el
f
o
r
SVM
as
s
h
o
wn
in
Fig
u
r
e
6
(
a)
,
at
8
n
eig
h
b
o
r
s
f
o
r
KNN
as
s
h
o
wn
in
Fig
u
r
e
6
(
b
)
an
d
4
0
esti
m
ato
r
s
f
o
r
r
an
d
o
m
f
o
r
est
m
o
d
els
as
s
h
o
wn
i
n
Fig
u
r
e
6
(
c)
.
T
h
er
ef
o
r
e,
f
o
r
co
n
d
u
ctin
g
f
u
r
th
er
ex
p
er
i
m
en
tatio
n
s
,
th
ese
p
ar
a
m
eter
s
ar
e
ch
o
s
en
a
n
d
f
ix
e
d
.
(
a)
(
b
)
(
c)
Fig
u
r
e
6
.
R
esu
lts
o
f
d
if
f
e
r
en
t
p
ar
am
eter
tu
n
in
g
;
(
a
)
p
ar
a
m
eter
tu
n
in
g
f
o
r
k
er
n
els
in
SVM
,
(
b
)
p
a
r
am
eter
tu
n
in
g
f
o
r
n
u
m
b
e
r
o
f
n
eig
h
b
o
u
r
s
p
ar
am
eter
i
n
KNN
an
d
(
c
)
p
ar
am
eter
tu
n
in
g
f
o
r
n
u
m
b
e
r
o
f
esti
m
ato
r
s
in
r
an
d
o
m
f
o
r
est
T
h
e
d
etailed
test
in
g
r
esu
lts
o
b
tain
ed
o
n
n
o
n
-
s
tr
atif
ied
p
ar
titi
o
n
b
ased
NAFL
D
d
ata
s
et
ar
e
s
h
o
wn
in
T
ab
le
1
.
T
h
e
r
esu
lts
s
h
o
w
b
est
ac
cu
r
ac
y
lev
el
o
f
9
3
p
er
ce
n
t
f
o
r
Naïv
e
B
ay
es
m
o
d
el.
Fo
r
m
o
s
t
o
f
th
e
m
o
d
els
th
e
ac
cu
r
ac
y
was
r
o
u
n
d
o
f
f
9
3
p
er
ce
n
t,
ex
ce
p
t
d
ec
is
io
n
t
r
ee
.
T
h
e
p
r
ec
is
io
n
v
alu
es
r
ep
o
r
ted
wer
e
lo
w
f
o
r
d
ec
is
io
n
tr
ee
a
n
d
KNN.
T
ab
l
e
2
s
h
o
w
th
e
test
in
g
r
esu
lts
o
n
NAFL
D
d
ataset
af
ter
u
s
in
g
s
tr
atif
ied
s
am
p
lin
g
.
No
t
m
u
ch
im
p
r
o
v
em
e
n
t
is
o
b
s
er
v
ed
in
ac
c
u
r
ac
y
v
alu
es
o
f
th
e
p
r
ed
ictio
n
,
h
o
wev
er
p
r
ec
is
io
n
lev
els
ar
e
im
p
r
o
v
e
d
f
o
r
all
th
e
p
r
ed
ictiv
e
m
o
d
els.
T
ab
le
1
.
P
r
ed
ictio
n
q
u
ality
r
esu
lts
o
f
n
o
n
-
s
tr
atif
ied
q
u
ality
i
m
p
r
o
v
e
d
NAFL
D
test
d
ata
P
r
e
d
i
c
t
i
v
e
m
o
d
e
l
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
Lo
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
0
.
9
2
8
0
.
6
3
2
0
.
9
3
0
.
9
0
N
a
ï
v
e
B
a
y
e
s
0
.
9
3
1
0
.
6
8
1
0
.
9
3
0
.
9
1
S
V
M
(
P
o
l
y
)
0
.
9
2
5
1
.
0
0
.
9
3
0
.
8
9
N
e
u
r
a
l
n
e
t
w
o
r
k
0
.
9
2
8
0
.
5
5
0
.
9
3
0
.
9
1
D
e
c
i
s
i
o
n
t
r
e
e
0
.
8
7
9
0
.
2
2
0
.
8
8
0
.
8
8
K
N
N
(
8
n
e
i
g
h
b
o
r
s)
0
.
9
2
7
0
.
5
9
6
0
.
9
3
0
.
9
0
R
a
n
d
o
m
f
o
r
e
s
t
(
4
0
e
st
i
ma
t
o
r
s)
0
.
9
2
5
0
.
5
1
4
0
.
9
3
0
.
9
1
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
2
1
4
-
2
2
2
220
T
ab
le
2
.
Pre
d
ictio
n
q
u
ality
r
esu
l
ts
o
f
s
tr
atif
ied
q
u
ality
im
p
r
o
v
ed
NAFL
D
test
d
ata
P
r
e
d
i
c
t
i
v
e
m
o
d
e
l
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
Lo
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
0
.
9
2
6
0
.
6
9
0
.
9
3
0
.
9
0
N
a
ï
v
e
B
a
y
e
s
0
.
9
2
6
0
.
6
0
7
0
.
9
3
0
.
9
1
S
V
M
(
P
o
l
y
)
0
.
9
2
2
1
.
0
0
.
9
2
0
.
8
9
N
e
u
r
a
l
n
e
t
w
o
r
k
0
.
9
2
9
0
.
7
1
7
0
.
9
3
0
.
9
1
D
e
c
i
s
i
o
n
t
r
e
e
0
.
8
8
4
0
.
2
7
5
0
.
8
8
0
.
8
9
K
N
N
(
8
n
e
i
g
h
b
o
r
s)
0
.
9
2
5
0
.
6
2
1
0
.
9
3
0
.
9
0
R
a
n
d
o
m
f
o
r
e
s
t
(
4
0
e
st
i
ma
t
o
r
s)
0
.
9
2
5
0
.
5
5
4
0
.
9
3
0
.
9
1
T
ab
le
3
s
h
o
ws
th
e
test
in
g
r
esu
lts
u
s
in
g
s
tr
atif
ied
d
is
tr
ib
u
ted
an
d
Up
s
ca
led
NAFL
D
d
ata
s
et.
A
q
u
ite
in
ter
esti
n
g
o
b
s
er
v
ati
o
n
f
o
r
th
e
r
esu
lts
o
b
tain
e
d
i
n
d
icate
a
b
alan
ce
d
r
esu
lt
f
o
r
a
cc
u
r
ac
y
as
well
a
s
p
r
ec
is
io
n
.
A
b
alan
ce
d
r
esu
lt
o
f
ac
cu
r
ac
y
an
d
p
r
ec
is
io
n
lead
to
b
etter
R
OC
cu
r
v
es
with
h
ig
h
er
AUC
v
alu
es,
wh
ich
is
a
s
tr
o
n
g
in
d
icatio
n
f
o
r
th
e
co
r
r
ec
tn
ess
o
f
th
e
d
ev
elo
p
ed
p
r
e
d
ictiv
e
m
o
d
el
u
s
in
g
U
p
s
ca
led
an
d
q
u
ality
en
h
an
ce
d
d
ataset.
R
OC
cu
r
v
es
f
o
r
s
tr
a
tifie
d
d
ata
f
o
r
th
e
r
esu
lts
o
f
T
ab
le
2
a
n
d
T
a
b
le
3
a
r
e
p
lo
t
ted
an
d
s
h
o
wn
in
Fig
u
r
e
7
.
T
ab
le
3
.
Pre
d
ictio
n
q
u
ality
r
esu
lts
o
f
s
tr
atif
ied
q
u
ality
im
p
r
o
v
ed
u
p
s
ca
led
N
AFLD
test
d
ata
P
r
e
d
i
c
t
i
v
e
m
o
d
e
l
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
Lo
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
0
.
8
6
9
0
.
7
0
4
0
.
8
7
0
.
8
4
N
a
ï
v
e
B
a
y
e
s
0
.
8
6
8
0
.
5
9
1
0
.
8
7
0
.
8
6
S
V
M
(
P
o
l
y
)
0
.
8
8
9
0
.
8
5
9
0
.
8
9
0
.
8
7
N
e
u
r
a
l
n
e
t
w
o
r
k
0
.
9
2
7
0
.
8
3
6
0
.
9
3
0
.
9
2
D
e
c
i
s
i
o
n
t
r
e
e
0
.
8
9
3
0
.
6
3
9
0
.
8
9
0
.
8
9
K
N
N
(
8
n
e
i
g
h
b
o
r
s)
0
.
9
3
0
0
.
9
3
7
0
.
9
3
0
.
9
2
R
a
n
d
o
m
f
o
r
e
s
t
(
4
0
e
st
i
ma
t
o
r
s)
0
.
9
3
3
0
.
9
0
8
0
.
9
3
0
.
9
3
R
OC
c
u
r
v
e
s
:
R
OC
cu
r
v
es
ar
e
also
g
en
er
ated
as
s
h
o
wn
in
Fig
u
r
e
7
.
Fig
u
r
e
7
(
a)
d
e
p
icts
th
e
p
lo
t
f
o
r
s
tr
atif
ied
d
ata,
wh
er
ea
s
Fig
u
r
e
7
(
b
)
s
h
o
ws
th
e
p
lo
t
f
o
r
s
tr
at
if
ied
u
p
s
ca
led
d
ata.
I
t
is
ev
id
en
t
th
at
R
OC
cu
r
v
e
s
h
o
wn
in
Fig
u
r
e
7
(
b
)
h
as
h
ig
h
er
AUC
v
alu
es,
th
e
r
ef
o
r
e
th
e
r
esu
lts
o
f
ac
c
u
r
ac
y
an
d
p
r
e
cisi
o
n
g
en
er
ated
f
o
r
s
tr
atif
ied
d
is
tr
ib
u
ted
u
p
s
ca
led
d
ata
ar
e
h
ig
h
l
y
r
eliab
le
an
d
in
d
icate
r
ea
lis
tic
ac
cu
r
a
cy
f
o
r
th
e
f
u
tu
r
e
p
r
ed
ictio
n
s
.
T
h
e
h
ig
h
est AUC is
r
ep
o
r
ted
f
o
r
n
e
u
r
al
n
etwo
r
k
m
o
d
el
an
d
r
an
d
o
m
f
o
r
est
m
o
d
el.
(
a)
(
b
)
Fig
u
r
e
7
.
R
OC
an
d
AUC v
alu
es f
o
r
(
a)
s
tr
atif
ied
d
is
tr
ib
u
ted
d
ata
an
d
(
b
)
s
tr
atif
ied
d
is
tr
ib
u
t
ed
u
p
s
ca
led
d
ata
4.
K
E
Y
T
AK
E
AWAY
S
R
ea
d
er
s
will
b
e
ab
le
to
u
n
d
er
s
tan
d
th
e
s
ig
n
if
ican
ce
o
f
d
ata
p
r
ep
r
o
ce
s
s
in
g
to
m
ed
ical
d
ata
f
o
r
ac
cu
r
ate
p
r
e
d
ictio
n
i
n
th
is
p
a
p
er
.
T
r
ai
n
in
g
an
d
test
in
g
d
at
a
p
r
ed
ictio
n
r
esu
lts
o
n
v
ar
ied
p
r
ed
ictio
n
q
u
ality
q
u
an
tific
atio
n
m
etr
ics
s
u
ch
“
ac
cu
r
ac
y
”
,
“
p
r
ec
is
io
n
”
,
“
r
ec
a
ll
”
,
an
d
“
F1
-
s
co
r
e
”
u
s
in
g
u
n
p
r
o
ce
s
s
ed
d
ata
a
n
d
p
r
o
ce
s
s
ed
d
ata
h
as
b
ee
n
d
o
cu
m
en
ted
f
o
r
s
ev
en
d
if
f
e
r
en
t
s
tate
o
f
th
e
ar
t
m
ac
h
in
e
lear
n
in
g
b
ased
p
r
ed
ictiv
e
m
o
d
els
n
am
e
d
“
l
o
g
is
tic
r
eg
r
e
s
s
io
n
”
,
“
Naïv
e
B
ay
es
”
,
“
SV
M
”
,
“
d
ec
is
io
n
tr
ee
”
,
“
n
eu
r
al
n
etwo
r
k
”
,
“
r
an
d
o
m
f
o
r
est
”
,
an
d
“
KNN
”
.
R
ea
d
er
s
will a
ls
o
b
e
ab
le
to
id
en
tify
ex
p
er
im
en
tal
r
esu
lts
o
f
v
ar
ied
p
y
th
o
n
-
b
ased
u
tili
ties
to
au
to
m
ate
th
e
q
u
ality
en
h
an
ce
m
en
t
p
r
o
ce
s
s
.
Py
th
o
n
u
tili
ties
p
r
esen
ted
h
er
e
ar
e
p
y
t
h
o
n
i
m
p
u
ter
an
d
p
y
th
o
n
s
m
o
te
u
tili
ty
to
en
h
an
ce
an
d
b
alan
ce
th
e
d
ata
s
ets
in
c
ase
o
f
im
b
alan
ce
class
d
is
tr
ib
u
tio
n
f
o
r
q
u
ality
en
h
an
ce
m
e
n
ts
an
d
r
ea
lis
tic
p
r
ed
ictio
n
s
u
s
in
g
eq
u
al
d
is
tr
ib
u
t
io
n
o
f
class
d
ata
s
ets.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
en
h
a
n
ce
d
p
r
ed
ictive
mo
d
el
lin
g
fr
a
mewo
r
k
fo
r
h
ig
h
ly
a
cc
u
r
a
te
…
(
N
id
h
i A
r
o
r
a
)
221
5.
CO
NCLU
SI
O
N
Pre
d
ictiv
e
an
aly
s
is
is
a
s
ig
n
if
ican
t
ar
ea
o
f
r
esear
c
h
in
m
ed
ical
i
n
f
o
r
m
atics
s
p
ec
if
ically
f
o
r
d
ev
elo
p
in
g
m
ac
h
in
e
lea
r
n
in
g
m
o
d
els
f
o
r
ch
r
o
n
ic
d
is
ea
s
es.
NAFL
D
is
o
n
e
s
u
ch
d
is
ea
s
e
wh
ich
is
im
p
ac
tin
g
q
u
ite
a
lar
g
e
n
u
m
b
er
o
f
in
d
iv
i
d
u
als n
o
w
a
d
ay
s
.
Hig
h
q
u
ality
p
r
ed
ictiv
e
m
o
d
els h
av
in
g
h
i
g
h
q
u
ality
in
d
icato
r
s
f
o
r
p
r
ed
ictio
n
ac
cu
r
ac
y
.
Su
c
h
m
o
d
els,
if
d
e
v
elo
p
ed
,
will
b
e
a
b
o
o
n
f
o
r
all
s
tak
eh
o
ld
er
s
i
n
th
e
h
ea
lth
s
ec
to
r
.
Ho
wev
er
,
d
u
e
to
s
ca
r
city
o
f
h
i
g
h
-
q
u
ality
r
ea
l
tim
e
clin
ical
d
atasets
,
q
u
ality
p
r
ed
ictio
n
with
h
ig
h
ac
cu
r
ac
y
is
a
ch
allen
g
e.
T
h
is
p
a
p
er
h
as
p
r
e
s
en
ted
a
m
o
d
u
lar
a
p
p
r
o
ac
h
with
s
y
s
tem
atic
p
h
ased
ap
p
licat
io
n
o
f
d
ata
q
u
ality
en
h
an
ce
m
e
n
t
s
tep
s
f
o
r
NAFL
D
clin
ical
o
b
s
er
v
atio
n
d
ata
s
ets
u
s
in
g
p
y
th
o
n
s
im
p
le
u
tili
ties
s
u
ch
as
im
p
u
ter
an
d
SMOT
E
.
SMOT
E
u
tili
ty
u
tili
ze
s
g
en
er
ativ
e
AI
m
et
h
o
d
o
lo
g
ies
to
u
p
s
ca
le
th
e
im
b
alan
ce
d
d
ataset.
T
h
e
g
en
er
ated
q
u
ality
NAFL
D
d
ataset
is
s
u
b
ject
ed
to
tr
ain
in
g
an
d
test
in
g
o
f
s
ev
en
s
tate
o
f
th
e
ar
t
m
ac
h
in
e
lear
n
in
g
p
r
ed
ictiv
e
m
o
d
els.
T
h
e
in
-
d
ep
th
e
m
p
ir
ical
a
n
aly
s
is
o
f
test
in
g
d
ata
p
r
ed
ictio
n
r
esu
lts
h
as
s
h
o
wn
im
p
r
o
v
em
e
n
t
in
th
e
p
r
ec
is
io
n
,
AUC
v
alu
es
o
f
R
OC
cu
r
v
e
in
d
icato
r
,
wh
ic
h
in
d
icate
s
s
ig
n
if
ica
n
ce
o
f
q
u
ality
im
p
r
o
v
e
d
d
ataset
f
o
r
n
af
ld
p
r
e
d
ictio
n
,
a
n
d
h
en
ce
p
av
in
g
a
w
ay
to
war
d
s
p
r
ed
ictio
n
o
f
o
th
er
d
is
ea
s
es
u
s
in
g
o
u
r
d
ep
icted
s
tep
b
y
s
tep
m
eth
o
d
o
lo
g
y
f
o
r
d
e
v
elo
p
in
g
h
ig
h
q
u
ality
p
r
ed
ictio
n
m
o
d
els in
m
ed
ic
al
in
f
o
r
m
atics.
Fu
tu
r
e
wo
r
k
:
th
e
c
o
n
d
u
cted
e
x
p
er
im
en
tatio
n
n
ee
d
s
to
b
e
ex
ten
d
ed
f
o
r
o
th
er
d
is
ea
s
es
with
r
ea
l
tim
e
d
atasets
.
th
e
wo
r
k
ca
n
b
e
ex
ten
d
ed
with
r
ea
l tim
e
test
in
g
wit
h
p
ar
allel
co
m
p
u
tatio
n
in
r
ea
l tim
e
en
v
ir
o
n
m
e
n
ts
.
I
m
p
ac
t o
f
d
ee
p
lear
n
in
g
c
an
b
e
ex
ten
d
ed
f
o
r
th
e
co
n
s
id
er
ed
d
ataset.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
K
i
v
i
mä
k
i
,
A
.
B
a
r
t
o
l
o
m
u
c
c
i
,
a
n
d
I
.
K
a
w
a
c
h
i
,
“
T
h
e
m
u
l
t
i
p
l
e
r
o
l
e
s
o
f
l
i
f
e
st
r
e
ss
i
n
me
t
a
b
o
l
i
c
d
i
s
o
r
d
e
r
s,
”
N
a
t
u
re
Re
v
i
e
w
s
En
d
o
c
ri
n
o
l
o
g
y
,
v
o
l
.
1
9
,
n
o
.
1
,
p
p
.
1
0
–
2
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
7
4
-
0
2
2
-
0
0
7
46
-
8.
[
2
]
N
.
S
t
e
f
a
n
a
n
d
K
.
C
u
si
,
“
A
g
l
o
b
a
l
v
i
e
w
o
f
t
h
e
i
n
t
e
r
p
l
a
y
b
e
t
w
e
e
n
n
o
n
-
a
l
c
o
h
o
l
i
c
f
a
t
t
y
l
i
v
e
r
d
i
s
e
a
s
e
a
n
d
d
i
a
b
e
t
e
s,
”
T
h
e
L
a
n
c
e
t
D
i
a
b
e
t
e
s
a
n
d
E
n
d
o
c
r
i
n
o
l
o
g
y
,
v
o
l
.
1
0
,
n
o
.
4
,
p
p
.
2
8
4
–
2
9
6
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
S
2
2
1
3
-
8
5
8
7
(
2
2
)
0
0
0
0
3
-
1.
[
3
]
S
.
D
e
y
e
t
a
l
.
,
“
H
u
ma
n
-
c
e
n
t
e
r
e
d
e
x
p
l
a
i
n
a
b
i
l
i
t
y
f
o
r
l
i
f
e
sc
i
e
n
c
e
s,
h
e
a
l
t
h
c
a
r
e
,
a
n
d
me
d
i
c
a
l
i
n
f
o
r
ma
t
i
c
s,”
P
a
t
t
e
r
n
s
,
v
o
l
.
3
,
n
o
.
5
,
p
.
1
0
0
4
9
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
t
e
r
.
2
0
2
2
.
1
0
0
4
9
3
.
[
4
]
L.
C
a
r
o
p
r
e
se
,
E.
V
o
c
a
t
u
r
o
,
a
n
d
E.
Z
u
mp
a
n
o
,
“
A
r
g
u
m
e
n
t
a
t
i
o
n
a
p
p
r
o
a
c
h
e
s
f
o
r
e
x
p
l
a
n
a
i
b
l
e
A
I
i
n
me
d
i
c
a
l
i
n
f
o
r
ma
t
i
c
s
,
”
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
6
,
p
.
2
0
0
1
0
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
sw
a
.
2
0
2
2
.
2
0
0
1
0
9
.
[
5
]
R
.
C
.
D
e
o
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
m
e
d
i
c
i
n
e
,
”
C
i
r
c
u
l
a
t
i
o
n
,
v
o
l
.
1
3
2
,
n
o
.
2
0
,
p
p
.
1
9
2
0
–
1
9
3
0
,
2
0
1
5
,
d
o
i
:
1
0
.
1
1
6
1
/
C
I
R
C
U
LA
TI
O
N
A
H
A
.
1
1
5
.
0
0
1
5
9
3
.
[
6
]
F
.
M
.
D
e
l
p
i
n
o
,
K
.
C
o
s
t
a
,
S
.
R
.
F
a
r
i
a
s,
A
.
D
.
P
.
C
h
i
a
v
e
g
a
t
t
o
F
i
l
h
o
,
R
.
A
.
A
r
c
ê
n
c
i
o
,
a
n
d
B
.
P
.
N
u
n
e
s,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
p
r
e
d
i
c
t
i
n
g
c
h
r
o
n
i
c
d
i
sea
ses:
a
sy
s
t
e
m
a
t
i
c
r
e
v
i
e
w
,
”
Pu
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
2
0
5
,
p
p
.
1
4
–
2
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
u
h
e
.
2
0
2
2
.
0
1
.
0
0
7
.
[
7
]
R
.
A
l
a
n
a
z
i
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
p
r
e
d
i
c
t
i
o
n
o
f
c
h
r
o
n
i
c
d
i
sea
ses
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
J
o
u
r
n
a
l
o
f
H
e
a
l
t
h
c
a
re
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
9
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
2
8
2
6
1
2
7
.
[
8
]
C
.
K
r
i
t
t
a
n
a
w
o
n
g
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
p
r
e
d
i
c
t
i
o
n
i
n
c
a
r
d
i
o
v
a
s
c
u
l
a
r
d
i
sea
s
e
s:
a
m
e
t
a
-
a
n
a
l
y
s
i
s,”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
0
,
n
o
.
1
,
p
.
1
6
0
5
7
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
0
-
7
2
6
8
5
-
1.
[
9
]
S
.
M
o
h
a
n
,
C
.
Th
i
r
u
m
a
l
a
i
,
a
n
d
G
.
S
r
i
v
a
s
t
a
v
a
,
“
Ef
f
e
c
t
i
v
e
h
e
a
r
t
d
i
s
e
a
s
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
h
y
b
r
i
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
8
1
5
4
2
–
8
1
5
5
4
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
2
3
7
0
7
.
[
1
0
]
T.
R
.
R
a
mes
h
,
U
.
K
.
L
i
l
h
o
r
e
,
M
.
P
o
o
n
g
o
d
i
,
S
.
S
i
ma
i
y
a
,
A
.
K
a
u
r
,
a
n
d
M
.
H
a
m
d
i
,
“
P
r
e
d
i
c
t
i
v
e
a
n
a
l
y
s
i
s
o
f
h
e
a
r
t
d
i
se
a
ses
w
i
t
h
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s,
”
M
a
l
a
y
si
a
n
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
0
2
2
,
n
o
.
S
p
e
c
i
a
l
I
ssu
e
1
,
p
p
.
1
3
2
–
1
4
8
,
2
0
2
2
,
d
o
i
:
1
0
.
2
2
4
5
2
/
m
j
c
s.
sp
2
0
2
2
n
o
1
.
1
0
.
[
1
1
]
M
.
M
.
A
h
s
a
n
a
n
d
Z.
S
i
d
d
i
q
u
e
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
s
e
d
h
e
a
r
t
d
i
s
e
a
se
d
i
a
g
n
o
s
i
s:
a
s
y
s
t
e
m
a
t
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
M
e
d
i
c
i
n
e
,
v
o
l
.
1
2
8
,
p
.
1
0
2
2
8
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
r
t
me
d
.
2
0
2
2
.
1
0
2
2
8
9
.
[
1
2
]
M
.
A
.
M
y
sz
c
z
y
n
s
k
a
e
t
a
l
.
,
“
A
p
p
l
i
c
a
t
i
o
n
s
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
o
d
i
a
g
n
o
si
s
a
n
d
t
r
e
a
t
me
n
t
o
f
n
e
u
r
o
d
e
g
e
n
e
r
a
t
i
v
e
d
i
sea
s
e
s,
”
N
a
t
u
re
Re
v
i
e
w
s N
e
u
ro
l
o
g
y
,
v
o
l
.
1
6
,
n
o
.
8
,
p
p
.
4
4
0
–
4
5
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
8
2
-
0
2
0
-
0
3
7
7
-
8.
[
1
3
]
A
.
M
.
Tă
u
ţ
a
n
,
B
.
I
o
n
e
s
c
u
,
a
n
d
E.
S
a
n
t
a
r
n
e
c
c
h
i
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
n
e
u
r
o
d
e
g
e
n
e
r
a
t
i
v
e
d
i
s
e
a
se
s:
a
r
e
v
i
e
w
o
f
a
v
a
i
l
a
b
l
e
t
o
o
l
s
w
i
t
h
a
f
o
c
u
s
o
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
M
e
d
i
c
i
n
e
,
v
o
l
.
1
1
7
,
p
.
1
0
2
0
8
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
r
t
me
d
.
2
0
2
1
.
1
0
2
0
8
1
.
[
1
4
]
K
.
M
.
K
i
n
g
sm
o
r
e
,
C
.
E.
P
u
g
l
i
s
i
,
A
.
C
.
G
r
a
mm
e
r
,
a
n
d
P
.
E.
Li
p
s
k
y
,
“
A
n
i
n
t
r
o
d
u
c
t
i
o
n
t
o
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
a
n
a
l
y
s
i
s o
f
i
t
s
u
se
i
n
r
h
e
u
ma
t
i
c
d
i
se
a
ses
,
”
N
a
t
u
re
Re
v
i
e
w
s
Rh
e
u
m
a
t
o
l
o
g
y
,
v
o
l
.
1
7
,
n
o
.
1
2
,
p
p
.
7
1
0
–
7
3
0
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
8
4
-
0
2
1
-
0
0
7
0
8
-
w.
[
1
5
]
M
.
Ji
a
n
g
,
Y
.
Li
,
C
.
Ji
a
n
g
,
L
.
Zh
a
o
,
X
.
Z
h
a
n
g
,
a
n
d
P
.
E.
L
i
p
s
k
y
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
r
h
e
u
m
a
t
i
c
d
i
se
a
ses
,
”
C
l
i
n
i
c
a
l
Re
v
i
e
w
s
i
n
Al
l
e
rg
y
a
n
d
I
m
m
u
n
o
l
o
g
y
,
v
o
l
.
6
0
,
n
o
.
1
,
p
p
.
9
6
–
1
1
0
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
0
1
6
-
0
2
0
-
0
8
8
0
5
-
6.
[
1
6
]
S
.
N
u
s
i
n
o
v
i
c
i
e
t
a
l
.
,
“
L
o
g
i
s
t
i
c
r
e
g
r
e
s
si
o
n
w
a
s
a
s
g
o
o
d
a
s
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
p
r
e
d
i
c
t
i
n
g
m
a
j
o
r
c
h
r
o
n
i
c
d
i
s
e
a
ses,
”
J
o
u
rn
a
l
o
f
C
l
i
n
i
c
a
l
Ep
i
d
e
m
i
o
l
o
g
y
,
v
o
l
.
1
2
2
,
p
p
.
5
6
–
6
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
c
l
i
n
e
p
i
.
2
0
2
0
.
0
3
.
0
0
2
.
[
1
7
]
G
.
Ta
r
g
h
e
r
,
K
.
E.
C
o
r
e
y
,
a
n
d
C
.
D
.
B
y
r
n
e
,
“
N
A
F
LD
,
a
n
d
c
a
r
d
i
o
v
a
s
c
u
l
a
r
a
n
d
c
a
r
d
i
a
c
d
i
sea
s
e
s:
f
a
c
t
o
r
s
i
n
f
l
u
e
n
c
i
n
g
r
i
s
k
,
p
r
e
d
i
c
t
i
o
n
a
n
d
t
r
e
a
t
me
n
t
,
”
D
i
a
b
e
t
e
s
a
n
d
Me
t
a
b
o
l
i
sm
,
v
o
l
.
4
7
,
n
o
.
2
,
p
.
1
0
1
2
1
5
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
i
a
b
e
t
.
2
0
2
0
.
1
0
1
2
1
5
.
[
1
8
]
G
.
L.
H
.
W
o
n
g
,
P
.
C
.
Y
u
e
n
,
A
.
J
.
M
a
,
A
.
W
.
H
.
C
h
a
n
,
H
.
H
.
W
.
L
e
u
n
g
,
a
n
d
V
.
W
.
S
.
W
o
n
g
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
p
r
e
d
i
c
t
i
o
n
o
f
n
o
n
-
a
l
c
o
h
o
l
i
c
f
a
t
t
y
l
i
v
e
r
d
i
s
e
a
se
a
n
d
f
i
b
r
o
s
i
s,”
J
o
u
r
n
a
l
o
f
G
a
s
t
ro
e
n
t
e
ro
l
o
g
y
a
n
d
H
e
p
a
t
o
l
o
g
y
(
A
u
st
r
a
l
i
a
)
,
v
o
l
.
3
6
,
n
o
.
3
,
p
p
.
5
4
3
–
5
5
0
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
1
1
/
j
g
h
.
1
5
3
8
5
.
[
1
9
]
C
.
C
.
W
u
e
t
a
l
.
,
“
P
r
e
d
i
c
t
i
o
n
o
f
f
a
t
t
y
l
i
v
e
r
d
i
se
a
se
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
,
”
C
o
m
p
u
t
e
r
Me
t
h
o
d
s
a
n
d
Pr
o
g
r
a
m
s
i
n
Bi
o
m
e
d
i
c
i
n
e
,
v
o
l
.
1
7
0
,
p
p
.
2
3
–
2
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
m
p
b
.
2
0
1
8
.
1
2
.
0
3
2
.
[
2
0
]
S
.
Q
i
n
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
s
si
f
i
e
r
s fo
r
scre
e
n
i
n
g
n
o
n
a
l
c
o
h
o
l
i
c
f
a
t
t
y
l
i
v
e
r
d
i
s
e
a
s
e
i
n
g
e
n
e
r
a
l
a
d
u
l
t
s
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
3
,
n
o
.
1
,
p
.
3
6
3
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
0
2
3
-
3
0
7
5
0
-
5.
[
2
1
]
J.
O
’
D
o
n
o
g
h
u
e
a
n
d
J
.
H
e
r
b
e
r
t
,
“
D
a
t
a
man
a
g
e
me
n
t
w
i
t
h
i
n
mH
e
a
l
t
h
e
n
v
i
r
o
n
men
t
s:
p
a
t
i
e
n
t
se
n
s
o
r
s,
m
o
b
i
l
e
d
e
v
i
c
e
s,
a
n
d
d
a
t
a
b
a
s
e
s,”
J
o
u
rn
a
l
o
f
D
a
t
a
a
n
d
I
n
f
o
rm
a
t
i
o
n
Q
u
a
l
i
t
y
,
v
o
l
.
4
,
n
o
.
1
,
p
p
.
1
–
2
0
,
2
0
1
2
,
d
o
i
:
1
0
.
1
1
4
5
/
2
3
7
8
0
1
6
.
2
3
7
8
0
2
1
.
[
2
2
]
N
.
A
r
o
r
a
,
S
.
S
r
i
v
a
s
t
a
v
a
,
R
.
A
g
a
r
w
a
l
,
V
.
M
e
h
n
d
i
r
a
t
t
a
,
a
n
d
A
.
Tr
i
p
a
t
h
i
,
“
D
i
a
b
e
t
e
s m
e
l
l
i
t
u
s
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
w
i
t
h
i
n
t
h
e
sc
o
p
e
o
f
a
g
e
n
e
r
i
c
f
r
a
mew
o
r
k
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r S
c
i
e
n
c
e
(
I
J
EEC
S
)
,
v
o
l
.
3
2
,
n
o
.
3
,
p
p
.
1
7
2
4
–
1
7
3
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
I
JEEC
S
.
V
3
2
.
I
3
.
P
P
1
7
2
4
-
1
7
3
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
1
,
J
an
u
ar
y
20
2
5
:
2
1
4
-
2
2
2
222
[
2
3
]
A
.
M
.
A
l
l
e
n
,
T.
M
.
T
h
e
r
n
e
a
u
,
J.
J.
La
r
so
n
,
A
.
C
o
w
a
r
d
,
V
.
K
.
S
o
m
e
r
s,
a
n
d
P
.
S
.
K
a
ma
t
h
,
“
N
o
n
a
l
c
o
h
o
l
i
c
f
a
t
t
y
l
i
v
e
r
d
i
se
a
se
i
n
c
i
d
e
n
c
e
a
n
d
i
m
p
a
c
t
o
n
me
t
a
b
o
l
i
c
b
u
r
d
e
n
a
n
d
d
e
a
t
h
:
A
2
0
y
e
a
r
-
c
o
mm
u
n
i
t
y
st
u
d
y
,
”
H
e
p
a
t
o
l
o
g
y
,
v
o
l
.
6
7
,
n
o
.
5
,
p
p
.
1
7
2
6
–
1
7
3
6
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
0
2
/
h
e
p
.
2
9
5
4
6
.
[
2
4
]
H
.
H
a
mm
a
d
A
l
h
a
r
b
i
a
n
d
M
.
K
i
m
u
r
a
,
“
M
i
ssi
n
g
d
a
t
a
i
mp
u
t
a
t
i
o
n
u
s
i
n
g
d
a
t
a
g
e
n
e
r
a
t
e
d
b
y
G
A
N
,
”
i
n
AC
M
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
Pro
c
e
e
d
i
n
g
S
e
r
i
e
s
,
2
0
2
0
,
p
p
.
7
3
–
7
7
,
d
o
i
:
1
0
.
1
1
4
5
/
3
4
1
8
6
8
8
.
3
4
1
8
7
0
1
.
[
2
5
]
R
.
B
l
a
g
u
s
a
n
d
L
.
L
u
sa
,
“
S
M
O
T
E
f
o
r
h
i
g
h
-
d
i
me
n
si
o
n
a
l
c
l
a
ss
-
i
mb
a
l
a
n
c
e
d
d
a
t
a
,
”
BM
C
Bi
o
i
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
4
,
n
o
.
1
,
p
.
1
0
6
,
2
0
1
3
,
d
o
i
:
1
0
.
1
1
8
6
/
1
4
7
1
-
2
1
0
5
-
14
-
1
0
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Nid
h
i
Ar
o
r
a
is
c
u
rre
n
tl
y
wo
rk
i
n
g
a
s
a
ss
o
c
iate
p
r
o
fe
ss
o
r
De
p
a
rtme
n
t
o
f
c
o
m
p
u
ter
sc
ien
c
e
,
Ka
li
n
d
i
Co
ll
e
g
e
,
Un
iv
e
rsit
y
o
f
De
lh
i
.
Wi
th
a
tea
c
h
in
g
e
x
p
e
rien
c
e
o
f
2
3
y
e
a
rs
a
n
d
a
P
h
.
D.
i
n
Co
m
p
u
ter
S
c
ien
c
e
,
Un
iv
e
rsit
y
o
f
De
l
h
i,
h
e
r
p
rima
ry
re
se
a
rc
h
a
re
a
s
a
re
so
c
ial
n
e
two
r
k
s,
n
a
t
u
re
i
n
sp
ired
c
o
m
p
u
ti
n
g
a
n
d
m
a
c
h
i
n
e
lea
rn
i
n
g
.
S
h
e
h
a
s
p
u
b
li
sh
e
d
m
a
n
y
p
e
e
rs
re
v
iew
e
d
re
se
a
rc
h
a
rti
c
les
in
i
n
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls o
f
re
p
u
te,
b
o
o
k
c
h
a
p
ters
,
a
n
d
h
a
s
a
lso
p
re
se
n
ted
m
a
n
y
re
se
a
rc
h
p
a
p
e
rs
in
v
a
rio
u
s
in
ter
n
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
o
f
ACM,
S
p
ri
n
g
e
r
a
n
d
IEE
E.
Dr.
Ni
d
h
i
Aro
ra
h
a
s
d
e
li
v
e
re
d
m
a
n
y
talk
s
o
n
late
st
re
se
a
rc
h
to
p
ics
su
c
h
a
s
“
Da
ta
S
c
ien
c
e
s”
,
“
e
-
c
o
n
ten
t
d
e
v
e
lo
p
m
e
n
t
”,
a
n
d
“
d
e
e
p
lea
rn
in
g
”
t
o
n
a
m
e
a
fe
w.
S
h
e
h
a
s
b
e
e
n
p
a
rt
o
f
m
a
n
y
a
d
m
i
n
istrativ
e
a
ss
ig
n
m
e
n
ts,
c
o
m
m
it
tee
s,
o
n
th
e
b
o
a
rd
o
f
tec
h
n
ica
l
p
r
o
g
ra
m
m
e
r
c
o
m
m
it
tee
,
a
n
d
a
c
te
d
a
s
a
re
v
iew
e
r
to
in
m
a
n
y
i
n
tern
a
ti
o
n
a
l
jo
u
rn
a
ls.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
id
h
iaro
ra
@k
a
li
n
d
i.
d
u
.
a
c
.
i
n
.
Dr
.
S
h
il
p
a
S
r
i
v
a
sta
v
a
is
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
a
n
d
c
h
a
ir
p
e
rso
n
o
f
th
e
c
o
m
m
it
te
e
‘
AI
P
o
li
c
y
re
c
o
m
m
e
n
d
a
ti
o
n
s
’
a
t
Ch
rist
Un
iv
e
rsity
,
Be
n
g
a
lu
r
u
.
S
h
e
p
o
ss
e
ss
e
s
a
P
h
.
D
.
Co
m
p
u
ter
S
c
ien
c
e
fro
m
Uttara
k
h
a
n
d
Tec
h
n
ica
l
U
n
iv
e
rsit
y
a
n
d
h
e
r
a
re
a
s
o
f
in
tere
st
i
n
c
lu
d
e
a
p
p
li
c
a
ti
o
n
o
f
s
o
ft
c
o
m
p
u
ti
n
g
i
n
m
e
d
ica
l
d
o
m
a
in
,
t
h
e
o
r
y
o
f
c
o
m
p
u
tatio
n
,
a
lg
o
rit
h
m
s,
a
n
d
h
e
a
lt
h
se
r
v
ice
s.
Cu
rre
n
tl
y
sh
e
i
s
g
u
id
i
n
g
t
h
re
e
P
h
.
D.
S
c
h
o
lars
a
n
d
p
u
b
li
s
h
e
d
m
a
n
y
p
e
e
rs
re
v
iew
e
d
re
se
a
rc
h
a
rti
c
les
in
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls
o
f
re
p
u
te,
o
n
e
p
a
ten
t,
b
o
o
k
c
h
a
p
ters
,
a
n
d
h
a
s
a
lso
p
re
se
n
ted
m
a
n
y
re
se
a
rc
h
p
a
p
e
rs
in
v
a
rio
u
s
in
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
o
f
ACM
,
S
p
rin
g
e
r
a
n
d
I
EE
E.
S
h
e
h
a
s
d
e
l
iv
e
re
d
tal
k
s
o
n
th
e
late
st
re
se
a
rc
h
t
o
p
ics
s
u
c
h
a
s
“
m
a
c
h
in
e
lea
rn
in
g
”
,
“
m
o
b
i
le
lea
rn
in
g
”
,
b
ri
n
g
y
o
u
r
o
wn
d
e
v
ice
”
,
to
n
a
m
e
a
fe
w.
S
h
e
h
a
s
a
lso
wo
rk
e
d
a
s
CO
-
P
I
in
a
re
se
a
rc
h
p
r
o
jec
t
in
c
o
ll
a
b
o
ra
ti
o
n
wit
h
IIT
Ro
o
rk
e
e
a
n
d
Li
v
e
rp
o
o
l
Ho
p
e
U
n
iv
e
rsit
y
UK
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sh
il
p
a
.
sriv
a
sta
v
a
2
0
1
5
@g
m
a
il
.
c
o
m
.
Dr
.
Aprna
Tr
ip
a
th
i
is
a
n
a
ss
is
tan
t
p
ro
fe
ss
o
r
i
n
th
e
D
e
p
a
rtme
n
t
o
f
D
a
ta
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
,
M
a
n
i
p
a
l
Un
iv
e
rsity
Ja
ip
u
r
,
Ja
ip
u
r
.
S
h
e
re
c
e
iv
e
d
h
e
r
b
a
c
h
e
lo
r
’
s
d
e
g
re
e
i
n
sc
ien
c
e
s
fro
m
Ka
n
p
u
r
Un
i
v
e
rsity
,
M
a
ste
r
’
s
i
n
C
o
m
p
u
ter
Ap
p
li
c
a
ti
o
n
s
fr
o
m
HBTI,
Ka
n
p
u
r
,
M
.
Tec
h
.
fr
o
m
Ba
n
a
sth
a
li
Un
i
v
e
r
sity
,
Ra
jas
th
a
n
a
n
d
P
h
.
D
.
f
ro
m
NIT
Allah
a
b
a
d
,
P
ra
y
a
g
ra
j.
Wi
th
o
v
e
r
1
5
y
e
a
rs
o
f
tea
c
h
in
g
a
n
d
re
se
a
rc
h
e
x
p
e
rien
c
e
,
h
e
r
sc
h
o
larly
c
o
n
tri
b
u
ti
o
n
s
c
a
n
b
e
fo
u
n
d
i
n
p
re
sti
g
io
u
s
n
a
ti
o
n
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s,
in
c
l
u
d
i
n
g
t
h
o
se
re
c
o
g
n
iz
e
d
b
y
S
CI
a
n
d
S
c
o
p
u
s.
He
r
a
re
a
s
o
f
sp
e
c
ializa
ti
o
n
in
c
l
u
d
e
s
o
ftwa
re
e
n
g
i
n
e
e
rin
g
,
so
ftwa
re
tes
ti
n
g
,
d
a
ta
v
is
u
a
li
z
a
ti
o
n
,
a
n
d
d
a
ta
stru
c
tu
re
s
a
n
d
a
lg
o
rit
h
m
s
.
No
tab
l
y
,
sh
e
h
a
s
a
u
th
o
re
d
a
b
o
o
k
ti
t
led
“
c
o
m
p
o
n
e
n
t
-
b
a
se
d
sy
ste
m
s:
e
stim
a
ti
n
g
e
f
fo
rts
u
sin
g
so
f
t
c
o
m
p
u
t
i
n
g
tec
h
n
iq
u
e
s
.
”
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
p
rn
a
.
tri
p
a
th
i@jai
p
u
r.
m
a
n
ip
a
l.
e
d
u
.
Dr
.
Va
r
u
n
a
G
u
p
ta
re
c
e
iv
e
d
P
h
.
D.
d
e
g
re
e
in
C
o
m
p
u
ter
S
c
ien
c
e
fro
m
CHRIST
Un
iv
e
rsity
,
Ba
n
g
a
lo
re
i
n
2
0
1
8
a
n
d
a
M
a
ste
r
o
f
C
o
m
p
u
ter
Ap
p
li
c
a
ti
o
n
s
(M
CA)
fro
m
AK
TU
,
Lu
c
k
n
o
w
I
n
d
ia.
S
h
e
is
c
u
rre
n
tl
y
wo
rk
i
n
g
a
s
a
ss
istan
t
p
r
o
fe
ss
o
r
in
t
h
e
S
c
h
o
o
l
o
f
S
c
ien
c
e
s,
CHRIST
(De
e
m
e
d
to
b
e
Un
i
v
e
rsity
)
De
lh
i
-
NCR,
G
h
a
z
iab
a
d
,
I
n
d
ia.
S
h
e
h
a
s
1
7
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
Alo
n
g
wit
h
P
h
.
D
.
stu
d
e
n
ts
Dr.
Va
ru
n
a
h
a
s
d
e
m
o
n
stra
ted
e
x
c
e
ll
e
n
t
su
p
e
rv
isi
o
n
a
b
i
li
ti
e
s
a
s
a
m
e
n
to
r
in
th
e
field
o
f
m
a
c
h
in
e
lea
rn
in
g
a
n
d
a
rti
ficia
l
i
n
telli
g
e
n
c
e
fo
r
P
.
G
.
a
n
d
U.G
.
stu
d
e
n
ts,
a
p
p
li
c
a
n
t
s.
S
e
v
e
ra
l
o
f
h
e
r
wo
r
k
s
h
a
v
e
b
e
e
n
p
u
b
l
ish
e
d
i
n
i
n
tern
a
ti
o
n
a
l
p
u
b
li
c
a
ti
o
n
s
a
n
d
c
o
n
fe
re
n
c
e
s.
S
h
e
h
a
s
o
r
g
a
n
ize
d
a
n
u
m
b
e
r
o
f
un
i
v
e
rsity
-
le
v
e
l
e
v
e
n
ts,
in
c
lu
d
in
g
q
u
a
li
ty
d
e
v
e
l
o
p
m
e
n
t
p
ro
g
ra
m
(QIP)
,
wo
r
k
sh
o
p
s,
a
n
d
fa
c
u
lt
y
d
e
v
e
lo
p
m
e
n
t
p
ro
g
ra
m
m
e
rs
.
S
h
e
se
rv
e
s
a
s
a
re
v
iew
e
r
in
m
a
n
y
S
c
o
p
u
s
a
n
d
W
o
S
i
n
d
e
x
e
d
j
o
u
r
n
a
ls.
S
h
e
h
a
s
d
e
m
o
n
stra
ted
re
m
a
rk
a
b
le
e
ffica
c
y
i
n
h
e
r
e
n
d
e
a
v
o
rs
to
a
c
ti
v
e
ly
in
v
o
lv
e
h
e
rse
lf
a
n
d
o
t
h
e
rs
a
ro
u
n
d
h
im
i
n
a
c
h
iev
i
n
g
a
c
a
d
e
m
ic
sa
ti
sfa
c
ti
o
n
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
v
a
ru
n
a
g
u
p
ta.cs
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.